Daily Papers

This paper presents a streaming extension for the Sortformer speaker diarization framework, whose key property is the arrival-time ordering of output speakers. The proposed approach employs an Arrival-Order Speaker Cache (AOSC) to store frame-level acoustic embeddings of previously observed speakers. Unlike conventional speaker-tracing buffers, AOSC orders embeddings by speaker index corresponding to their arrival time order, and is dynamically updated by selecting frames with the highest scores based on the model's past predictions. Notably, the number of stored embeddings per speaker is determined dynamically by the update mechanism, ensuring efficient cache utilization and precise speaker tracking. Experiments on benchmark datasets confirm the effectiveness and flexibility of our approach, even in low-latency setups. These results establish Streaming Sortformer as a robust solution for real-time multi-speaker tracking and a foundation for streaming multi-talker speech processing.

We propose the SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation learning framework. Unlike previous works on speech representation learning, which learns multilingual contextual speech embedding at the resolution of an acoustic frame (10-20ms), this work focuses on learning multimodal (speech-text) multilingual speech embedding at the resolution of a sentence (5-10s) such that the embedding vector space is semantically aligned across different languages. We combine state-of-the-art multilingual acoustic frame-level speech representation learning model XLS-R with the Language Agnostic BERT Sentence Embedding (LaBSE) model to create an utterance-level multimodal multilingual speech encoder SAMU-XLSR. Although we train SAMU-XLSR with only multilingual transcribed speech data, cross-lingual speech-text and speech-speech associations emerge in its learned representation space. To substantiate our claims, we use SAMU-XLSR speech encoder in combination with a pre-trained LaBSE text sentence encoder for cross-lingual speech-to-text translation retrieval, and SAMU-XLSR alone for cross-lingual speech-to-speech translation retrieval. We highlight these applications by performing several cross-lingual text and speech translation retrieval tasks across several datasets.

Large-scale pre-trained image-text models demonstrate remarkable versatility across diverse tasks, benefiting from their robust representational capabilities and effective multimodal alignment. We extend the application of these models, specifically CLIP, to the domain of sound source localization. Unlike conventional approaches, we employ the pre-trained CLIP model without explicit text input, relying solely on the audio-visual correspondence. To this end, we introduce a framework that translates audio signals into tokens compatible with CLIP's text encoder, yielding audio-driven embeddings. By directly using these embeddings, our method generates audio-grounded masks for the provided audio, extracts audio-grounded image features from the highlighted regions, and aligns them with the audio-driven embeddings using the audio-visual correspondence objective. Our findings suggest that utilizing pre-trained image-text models enable our model to generate more complete and compact localization maps for the sounding objects. Extensive experiments show that our method outperforms state-of-the-art approaches by a significant margin.

Recent multi-modal audio-language models (ALMs) excel at text-audio retrieval but struggle with frame-wise audio understanding. Prior works use temporal-aware labels or unsupervised training to improve frame-wise capabilities, but they still lack fine-grained labeling capability to pinpoint when an event occurs. While traditional sound event detection models can precisely localize events, they are limited to pre-defined categories, making them ineffective for real-world scenarios with out-of-distribution events. In this work, we introduce FLAM, an open-vocabulary contrastive audio-language model capable of localizing specific sound events. FLAM employs a memory-efficient and calibrated frame-wise objective with logit adjustment to address spurious correlations, such as event dependencies and label imbalances during training. To enable frame-wise supervision, we leverage a large-scale dataset with diverse audio events, LLM-generated captions and simulation. Experimental results and case studies demonstrate that FLAM significantly improves the open-vocabulary localization capability while maintaining strong performance in global retrieval and downstream tasks.

We introduce SONAR, a new multilingual and multimodal fixed-size sentence embedding space. Our single text encoder, covering 200 languages, substantially outperforms existing sentence embeddings such as LASER3 and LabSE on the xsim and xsim++ multilingual similarity search tasks. Speech segments can be embedded in the same SONAR embedding space using language-specific speech encoders trained in a teacher-student setting on speech transcription data. Our encoders outperform existing speech encoders on similarity search tasks. We also provide a text decoder for 200 languages, which allows us to perform text-to-text and speech-to-text machine translation, including for zero-shot language and modality combinations. Our text-to-text results are competitive compared to the state-of-the-art NLLB~1B model, despite the fixed-size bottleneck representation. Our zero-shot speech-to-text translation results compare favorably with strong supervised baselines such as Whisper.

In this paper, we propose a new multi-modal task, termed audio-visual instance segmentation (AVIS), which aims to simultaneously identify, segment and track individual sounding object instances in audible videos. To facilitate this research, we introduce a high-quality benchmark named AVISeg, containing over 90K instance masks from 26 semantic categories in 926 long videos. Additionally, we propose a strong baseline model for this task. Our model first localizes sound source within each frame, and condenses object-specific contexts into concise tokens. Then it builds long-range audio-visual dependencies between these tokens using window-based attention, and tracks sounding objects among the entire video sequences. Extensive experiments reveal that our method performs best on AVISeg, surpassing the existing methods from related tasks. We further conduct the evaluation on several multi-modal large models. Unfortunately, they exhibits subpar performance on instance-level sound source localization and temporal perception. We expect that AVIS will inspire the community towards a more comprehensive multi-modal understanding. Dataset and code is available at https://github.com/ruohaoguo/avis.

We propose Wav2CLIP, a robust audio representation learning method by distilling from Contrastive Language-Image Pre-training (CLIP). We systematically evaluate Wav2CLIP on a variety of audio tasks including classification, retrieval, and generation, and show that Wav2CLIP can outperform several publicly available pre-trained audio representation algorithms. Wav2CLIP projects audio into a shared embedding space with images and text, which enables multimodal applications such as zero-shot classification, and cross-modal retrieval. Furthermore, Wav2CLIP needs just ~10% of the data to achieve competitive performance on downstream tasks compared with fully supervised models, and is more efficient to pre-train than competing methods as it does not require learning a visual model in concert with an auditory model. Finally, we demonstrate image generation from Wav2CLIP as qualitative assessment of the shared embedding space. Our code and model weights are open sourced and made available for further applications.

Recently, there has been an increasing focus on audio-text cross-modal learning. However, most of the existing audio-text datasets contain only simple descriptions of sound events. Compared with classification labels, the advantages of such descriptions are significantly limited. In this paper, we first analyze the detailed information that human descriptions of audio may contain beyond sound event labels. Based on the analysis, we propose an automatic pipeline for curating audio-text pairs with rich details. Leveraging the property that sounds can be mixed and concatenated in the time domain, we control details in four aspects: temporal relationship, loudness, speaker identity, and occurrence number, in simulating audio mixtures. Corresponding details are transformed into captions by large language models. Audio-text pairs with rich details in text descriptions are thereby obtained. We validate the effectiveness of our pipeline with a small amount of simulated data, demonstrating that the simulated data enables models to learn detailed audio captioning.

Automatic transcriptions of consumer-generated multi-media content such as "Youtube" videos still exhibit high word error rates. Such data typically occupies a very broad domain, has been recorded in challenging conditions, with cheap hardware and a focus on the visual modality, and may have been post-processed or edited. In this paper, we extend our earlier work on adapting the acoustic model of a DNN-based speech recognition system to an RNN language model and show how both can be adapted to the objects and scenes that can be automatically detected in the video. We are working on a corpus of "how-to" videos from the web, and the idea is that an object that can be seen ("car"), or a scene that is being detected ("kitchen") can be used to condition both models on the "context" of the recording, thereby reducing perplexity and improving transcription. We achieve good improvements in both cases and compare and analyze the respective reductions in word error rate. We expect that our results can be used for any type of speech processing in which "context" information is available, for example in robotics, man-machine interaction, or when indexing large audio-visual archives, and should ultimately help to bring together the "video-to-text" and "speech-to-text" communities.

In this paper we present the first model for directly synthesizing fluent, natural-sounding spoken audio captions for images that does not require natural language text as an intermediate representation or source of supervision. Instead, we connect the image captioning module and the speech synthesis module with a set of discrete, sub-word speech units that are discovered with a self-supervised visual grounding task. We conduct experiments on the Flickr8k spoken caption dataset in addition to a novel corpus of spoken audio captions collected for the popular MSCOCO dataset, demonstrating that our generated captions also capture diverse visual semantics of the images they describe. We investigate several different intermediate speech representations, and empirically find that the representation must satisfy several important properties to serve as drop-in replacements for text.

We propose a pre-training pipeline for audio spectrogram transformers for frame-level sound event detection tasks. On top of common pre-training steps, we add a meticulously designed training routine on AudioSet frame-level annotations. This includes a balanced sampler, aggressive data augmentation, and ensemble knowledge distillation. For five transformers, we obtain a substantial performance improvement over previously available checkpoints both on AudioSet frame-level predictions and on frame-level sound event detection downstream tasks, confirming our pipeline's effectiveness. We publish the resulting checkpoints that researchers can directly fine-tune to build high-performance models for sound event detection tasks.

Text-to-video retrieval requires precise alignment between language and temporally rich video signals. Existing methods predominantly exploit visual cues and often overlook complementary audio semantics or adopt coarse fusion strategies, leading to suboptimal multimodal representations. We present GAID, a framework that jointly address this gap via two key components: (i) a Frame-level Gated Fusion (FGF) that adaptively integrates audio and visual features under textual guidance, enabling fine-grained temporal alignment; and (ii) a Directional Adaptive Semantic Perturbation (DASP) that injects structure-aware perturbations into text embeddings, enhancing robustness and discrimination without incurring multi-pass inference. These modules complement each other -- fusion reduces modality gaps while perturbation regularizes cross-modal matching -- yielding more stable and expressive representations. Extensive experiments on MSR-VTT, DiDeMo, LSMDC, and VATEX show consistent state-of-the-art results across all retrieval metrics with notable efficiency gains. Our code is available at https://github.com/YangBowenn/GAID.

We present PandaGPT, an approach to emPower large lANguage moDels with visual and Auditory instruction-following capabilities. Our pilot experiments show that PandaGPT can perform complex tasks such as detailed image description generation, writing stories inspired by videos, and answering questions about audios. More interestingly, PandaGPT can take multimodal inputs simultaneously and compose their semantics naturally. For example, PandaGPT can connect how objects look in an image/video and how they sound in an audio. To do so, PandaGPT combines the multimodal encoders from ImageBind and the large language models from Vicuna. Notably, only aligned image-text pairs are required for the training of PandaGPT. Thanks to the strong capability of ImageBind in embedding data from different modalities into the same space, PandaGPT displays emergent, i.e. zero-shot, cross-modal behaviors for data other than image and text (e.g., video, audio, depth, thermal, and IMU). We hope that PandaGPT serves as an initial step toward building AGI that can perceive and understand inputs in different modalities holistically, as we humans do. Our project page is at https://panda-gpt.github.io/.

In this paper our objectives are, first, networks that can embed audio and visual inputs into a common space that is suitable for cross-modal retrieval; and second, a network that can localize the object that sounds in an image, given the audio signal. We achieve both these objectives by training from unlabelled video using only audio-visual correspondence (AVC) as the objective function. This is a form of cross-modal self-supervision from video. To this end, we design new network architectures that can be trained for cross-modal retrieval and localizing the sound source in an image, by using the AVC task. We make the following contributions: (i) show that audio and visual embeddings can be learnt that enable both within-mode (e.g. audio-to-audio) and between-mode retrieval; (ii) explore various architectures for the AVC task, including those for the visual stream that ingest a single image, or multiple images, or a single image and multi-frame optical flow; (iii) show that the semantic object that sounds within an image can be localized (using only the sound, no motion or flow information); and (iv) give a cautionary tale on how to avoid undesirable shortcuts in the data preparation.

Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds, music, and speech. Although models have achieved remarkable performance, there is still a performance gap with task-specific models. In this paper, we propose a Contrastive Language-Audio Pretraining model that is pretrained with a diverse collection of 4.6M audio-text pairs employing two innovative encoders for Zero-Shot inference. To learn audio representations, we trained an audio encoder on 22 audio tasks, instead of the standard training of sound event classification. To learn language representations, we trained an autoregressive decoder-only model instead of the standard encoder-only models. Then, the audio and language representations are brought into a joint multimodal space using Contrastive Learning. We used our encoders to improve the downstream performance by a margin. We extensively evaluated the generalization of our representations on 26 downstream tasks, the largest in the literature. Our model achieves state of the art results in several tasks leading the way towards general-purpose audio representations.

Audio captioning aims to generate text descriptions from environmental sounds. One challenge of audio captioning is the difficulty of the generalization due to the lack of audio-text paired training data. In this work, we propose a simple yet effective method of dealing with small-scaled datasets by leveraging a pre-trained language model. We keep the language model frozen to maintain the expressivity for text generation, and we only learn to extract global and temporal features from the input audio. To bridge a modality gap between the audio features and the language model, we employ mapping networks that translate audio features to the continuous vectors the language model can understand, called prefixes. We evaluate our proposed method on the Clotho and AudioCaps dataset and show our method outperforms prior arts in diverse experimental settings.

Automatic detection of phoneme or word-like units is one of the core objectives in zero-resource speech processing. Recent attempts employ self-supervised training methods, such as contrastive predictive coding (CPC), where the next frame is predicted given past context. However, CPC only looks at the audio signal's frame-level structure. We overcome this limitation with a segmental contrastive predictive coding (SCPC) framework that can model the signal structure at a higher level e.g. at the phoneme level. In this framework, a convolutional neural network learns frame-level representation from the raw waveform via noise-contrastive estimation (NCE). A differentiable boundary detector finds variable-length segments, which are then used to optimize a segment encoder via NCE to learn segment representations. The differentiable boundary detector allows us to train frame-level and segment-level encoders jointly. Typically, phoneme and word segmentation are treated as separate tasks. We unify them and experimentally show that our single model outperforms existing phoneme and word segmentation methods on TIMIT and Buckeye datasets. We analyze the impact of boundary threshold and when is the right time to include the segmental loss in the learning process.

This work presents a framework based on feature disentanglement to learn speaker embeddings that are robust to environmental variations. Our framework utilises an auto-encoder as a disentangler, dividing the input speaker embedding into components related to the speaker and other residual information. We employ a group of objective functions to ensure that the auto-encoder's code representation - used as the refined embedding - condenses only the speaker characteristics. We show the versatility of our framework through its compatibility with any existing speaker embedding extractor, requiring no structural modifications or adaptations for integration. We validate the effectiveness of our framework by incorporating it into two popularly used embedding extractors and conducting experiments across various benchmarks. The results show a performance improvement of up to 16%. We release our code for this work to be available https://github.com/kaistmm/voxceleb-disentangler

We consider the task of retrieving audio using free-form natural language queries. To study this problem, which has received limited attention in the existing literature, we introduce challenging new benchmarks for text-based audio retrieval using text annotations sourced from the Audiocaps and Clotho datasets. We then employ these benchmarks to establish baselines for cross-modal audio retrieval, where we demonstrate the benefits of pre-training on diverse audio tasks. We hope that our benchmarks will inspire further research into cross-modal text-based audio retrieval with free-form text queries.

The objectives of this work are cross-modal text-audio and audio-text retrieval, in which the goal is to retrieve the audio content from a pool of candidates that best matches a given written description and vice versa. Text-audio retrieval enables users to search large databases through an intuitive interface: they simply issue free-form natural language descriptions of the sound they would like to hear. To study the tasks of text-audio and audio-text retrieval, which have received limited attention in the existing literature, we introduce three challenging new benchmarks. We first construct text-audio and audio-text retrieval benchmarks from the AudioCaps and Clotho audio captioning datasets. Additionally, we introduce the SoundDescs benchmark, which consists of paired audio and natural language descriptions for a diverse collection of sounds that are complementary to those found in AudioCaps and Clotho. We employ these three benchmarks to establish baselines for cross-modal text-audio and audio-text retrieval, where we demonstrate the benefits of pre-training on diverse audio tasks. We hope that our benchmarks will inspire further research into audio retrieval with free-form text queries. Code, audio features for all datasets used, and the SoundDescs dataset are publicly available at https://github.com/akoepke/audio-retrieval-benchmark.

This paper presents that the masked-modeling principle driving the success of large foundational vision models can be effectively applied to audio by making predictions in a latent space. We introduce Audio-based Joint-Embedding Predictive Architecture (A-JEPA), a simple extension method for self-supervised learning from the audio spectrum. Following the design of I-JEPA, our A-JEPA encodes visible audio spectrogram patches with a curriculum masking strategy via context encoder, and predicts the representations of regions sampled at well-designed locations. The target representations of those regions are extracted by the exponential moving average of context encoder, i.e., target encoder, on the whole spectrogram. We find it beneficial to transfer random block masking into time-frequency aware masking in a curriculum manner, considering the complexity of highly correlated in local time and frequency in audio spectrograms. To enhance contextual semantic understanding and robustness, we fine-tune the encoder with a regularized masking on target datasets, instead of input dropping or zero. Empirically, when built with Vision Transformers structure, we find A-JEPA to be highly scalable and sets new state-of-the-art performance on multiple audio and speech classification tasks, outperforming other recent models that use externally supervised pre-training.

Limited diversity in standardized benchmarks for evaluating audio representation learning (ARL) methods may hinder systematic comparison of current methods' capabilities. We present ARCH, a comprehensive benchmark for evaluating ARL methods on diverse audio classification domains, covering acoustic events, music, and speech. ARCH comprises 12 datasets, that allow us to thoroughly assess pre-trained SSL models of different sizes. ARCH streamlines benchmarking of ARL techniques through its unified access to a wide range of domains and its ability to readily incorporate new datasets and models. To address the current lack of open-source, pre-trained models for non-speech audio, we also release new pre-trained models that demonstrate strong performance on non-speech datasets. We argue that the presented wide-ranging evaluation provides valuable insights into state-of-the-art ARL methods, and is useful to pinpoint promising research directions.

We present DenseAV, a novel dual encoder grounding architecture that learns high-resolution, semantically meaningful, and audio-visually aligned features solely through watching videos. We show that DenseAV can discover the ``meaning'' of words and the ``location'' of sounds without explicit localization supervision. Furthermore, it automatically discovers and distinguishes between these two types of associations without supervision. We show that DenseAV's localization abilities arise from a new multi-head feature aggregation operator that directly compares dense image and audio representations for contrastive learning. In contrast, many other systems that learn ``global'' audio and video representations cannot localize words and sound. Finally, we contribute two new datasets to improve the evaluation of AV representations through speech and sound prompted semantic segmentation. On these and other datasets we show DenseAV dramatically outperforms the prior art on speech and sound prompted semantic segmentation. DenseAV outperforms the previous state-of-the-art, ImageBind, on cross-modal retrieval using fewer than half of the parameters. Project Page: https://aka.ms/denseav{https://aka.ms/denseav}

The last year has seen astonishing progress in text-prompted image generation premised on the idea of a cross-modal representation space in which the text and image domains are represented jointly. In ASR, this idea has found application as joint speech-text encoders that can scale to the capacities of very large parameter models by being trained on both unpaired speech and text. While these methods show promise, they have required special treatment of the sequence-length mismatch inherent in speech and text, either by up-sampling heuristics or an explicit alignment model. In this work, we offer evidence that joint speech-text encoders naturally achieve consistent representations across modalities by disregarding sequence length, and argue that consistency losses could forgive length differences and simply assume the best alignment. We show that such a loss improves downstream WER in both a large-parameter monolingual and multilingual system.

Self-supervised speech representation learning has become essential for extracting meaningful features from untranscribed audio. Recent advances highlight the potential of deriving discrete symbols from the features correlated with linguistic units, which enables text-less training across diverse tasks. In particular, sentence-level Self-Distillation of the pretrained HuBERT (SD-HuBERT) induces syllabic structures within latent speech frame representations extracted from an intermediate Transformer layer. In SD-HuBERT, sentence-level representation is accumulated from speech frame features through self-attention layers using a special CLS token. However, we observe that the information aggregated in the CLS token correlates more with speaker identity than with linguistic content. To address this, we propose a speech-only self-supervised fine-tuning approach that separates syllabic units from speaker information. Our method introduces speaker perturbation as data augmentation and adopts a frame-level training objective to prevent the CLS token from aggregating paralinguistic information. Experimental results show that our approach surpasses the current state-of-the-art method in most syllable segmentation and syllabic unit quality metrics on Librispeech, underscoring its effectiveness in promoting syllabic organization within speech-only models.

Joint embedding spaces have significantly advanced music understanding and generation by linking text and audio through multimodal contrastive learning. However, these approaches face large memory requirement limitations due to relying on large batch sizes to effectively utilize negative samples. Further, multimodal joint embedding spaces suffer from a modality gap wherein embeddings from different modalities lie in different manifolds of the embedding space. To address these challenges, we propose Siamese Language-Audio Pretraining (SLAP), a novel multimodal pretraining framework that allows learning powerful representations without negative samples. SLAP adapts the Bootstrap Your Own Latent (BYOL) paradigm for multimodal audio-text training, promoting scalability in training multimodal embedding spaces. We illustrate the ability of our model to learn meaningful relationships between music and text -- specifically, we show that SLAP outperforms CLAP on tasks such as text-music retrieval and zero-shot classification. We also observe competitive downstream performance on several MIR tasks, including with larger or supervised models (genre and instrument classification, auto-tagging). Additionally, our approach has attractive properties, such as a quantifiably reduced modality gap and improved robustness to batch size variations on retrieval performance. Finally, its novel formulation unlocks large-scale training on a single GPU through gradient accumulation.

Effectively steering hearable devices requires understanding the acoustic environment around the user. In the computational analysis of sound scenes, foundation models have emerged as the state of the art to produce high-performance, robust, multi-purpose audio representations. We introduce and release Deep Evaluation of Audio Representations (DEAR), the first dataset and benchmark to evaluate the efficacy of foundation models in capturing essential acoustic properties for hearables. The dataset includes 1,158 audio tracks, each 30 seconds long, created by spatially mixing proprietary monologues with commercial, high-quality recordings of everyday acoustic scenes. Our benchmark encompasses eight tasks that assess the general context, speech sources, and technical acoustic properties of the audio scenes. Through our evaluation of four general-purpose audio representation models, we demonstrate that the BEATs model significantly surpasses its counterparts. This superiority underscores the advantage of models trained on diverse audio collections, confirming their applicability to a wide array of auditory tasks, including encoding the environment properties necessary for hearable steering. The DEAR dataset and associated code are available at https://dear-dataset.github.io.

Music tagging and content-based retrieval systems have traditionally been constructed using pre-defined ontologies covering a rigid set of music attributes or text queries. This paper presents MuLan: a first attempt at a new generation of acoustic models that link music audio directly to unconstrained natural language music descriptions. MuLan takes the form of a two-tower, joint audio-text embedding model trained using 44 million music recordings (370K hours) and weakly-associated, free-form text annotations. Through its compatibility with a wide range of music genres and text styles (including conventional music tags), the resulting audio-text representation subsumes existing ontologies while graduating to true zero-shot functionalities. We demonstrate the versatility of the MuLan embeddings with a range of experiments including transfer learning, zero-shot music tagging, language understanding in the music domain, and cross-modal retrieval applications.

Improving text representation has attracted much attention to achieve expressive text-to-speech (TTS). However, existing works only implicitly learn the prosody with masked token reconstruction tasks, which leads to low training efficiency and difficulty in prosody modeling. We propose CLAPSpeech, a cross-modal contrastive pre-training framework that explicitly learns the prosody variance of the same text token under different contexts. Specifically, 1) We encourage the model to connect the text context with its corresponding prosody pattern in the joint multi-modal space with the elaborate design of the encoder inputs and contrastive loss; 2) We introduce a multi-scale pre-training pipeline to capture prosody patterns in multiple levels. We show how to incorporate CLAPSpeech into existing TTS models for better prosody. Experiments on three datasets not only show that CLAPSpeech could improve the prosody prediction for existing TTS methods, but also demonstrate its generalization ability to adapt to multiple languages and multi-speaker TTS. We also deeply analyze the principle behind the performance of CLAPSpeech. Ablation studies demonstrate the necessity of each component in our method. Source code and audio samples are available at https://clapspeech.github.io.

In a range of recent works, object-centric architectures have been shown to be suitable for unsupervised scene decomposition in the vision domain. Inspired by these methods we present AudioSlots, a slot-centric generative model for blind source separation in the audio domain. AudioSlots is built using permutation-equivariant encoder and decoder networks. The encoder network based on the Transformer architecture learns to map a mixed audio spectrogram to an unordered set of independent source embeddings. The spatial broadcast decoder network learns to generate the source spectrograms from the source embeddings. We train the model in an end-to-end manner using a permutation invariant loss function. Our results on Libri2Mix speech separation constitute a proof of concept that this approach shows promise. We discuss the results and limitations of our approach in detail, and further outline potential ways to overcome the limitations and directions for future work.

We introduce SLED, an alternative approach to speech language modeling by encoding speech waveforms into sequences of continuous latent representations and modeling them autoregressively using an energy distance objective. The energy distance offers an analytical measure of the distributional gap by contrasting simulated and target samples, enabling efficient training to capture the underlying continuous autoregressive distribution. By bypassing reliance on residual vector quantization, SLED avoids discretization errors and eliminates the need for the complicated hierarchical architectures common in existing speech language models. It simplifies the overall modeling pipeline while preserving the richness of speech information and maintaining inference efficiency. Empirical results demonstrate that SLED achieves strong performance in both zero-shot and streaming speech synthesis, showing its potential for broader applications in general-purpose speech language models.

Self supervised representation learning has recently attracted a lot of research interest for both the audio and visual modalities. However, most works typically focus on a particular modality or feature alone and there has been very limited work that studies the interaction between the two modalities for learning self supervised representations. We propose a framework for learning audio representations guided by the visual modality in the context of audiovisual speech. We employ a generative audio-to-video training scheme in which we animate a still image corresponding to a given audio clip and optimize the generated video to be as close as possible to the real video of the speech segment. Through this process, the audio encoder network learns useful speech representations that we evaluate on emotion recognition and speech recognition. We achieve state of the art results for emotion recognition and competitive results for speech recognition. This demonstrates the potential of visual supervision for learning audio representations as a novel way for self-supervised learning which has not been explored in the past. The proposed unsupervised audio features can leverage a virtually unlimited amount of training data of unlabelled audiovisual speech and have a large number of potentially promising applications.

Recent work has explored sequence-to-sequence latent variable models for expressive speech synthesis (supporting control and transfer of prosody and style), but has not presented a coherent framework for understanding the trade-offs between the competing methods. In this paper, we propose embedding capacity (the amount of information the embedding contains about the data) as a unified method of analyzing the behavior of latent variable models of speech, comparing existing heuristic (non-variational) methods to variational methods that are able to explicitly constrain capacity using an upper bound on representational mutual information. In our proposed model (Capacitron), we show that by adding conditional dependencies to the variational posterior such that it matches the form of the true posterior, the same model can be used for high-precision prosody transfer, text-agnostic style transfer, and generation of natural-sounding prior samples. For multi-speaker models, Capacitron is able to preserve target speaker identity during inter-speaker prosody transfer and when drawing samples from the latent prior. Lastly, we introduce a method for decomposing embedding capacity hierarchically across two sets of latents, allowing a portion of the latent variability to be specified and the remaining variability sampled from a learned prior. Audio examples are available on the web.

Recovering the masked speech frames is widely applied in speech representation learning. However, most of these models use random masking in the pre-training. In this work, we proposed two kinds of masking approaches: (1) speech-level masking, making the model to mask more speech segments than silence segments, (2) phoneme-level masking, forcing the model to mask the whole frames of the phoneme, instead of phoneme pieces. We pre-trained the model via these two approaches, and evaluated on two downstream tasks, phoneme classification and speaker recognition. The experiments demonstrated that the proposed masking approaches are beneficial to improve the performance of speech representation.

We explore a new task for audio-visual-language modeling called fine-grained audible video description (FAVD). It aims to provide detailed textual descriptions for the given audible videos, including the appearance and spatial locations of each object, the actions of moving objects, and the sounds in videos. Existing visual-language modeling tasks often concentrate on visual cues in videos while undervaluing the language and audio modalities. On the other hand, FAVD requires not only audio-visual-language modeling skills but also paragraph-level language generation abilities. We construct the first fine-grained audible video description benchmark (FAVDBench) to facilitate this research. For each video clip, we first provide a one-sentence summary of the video, ie, the caption, followed by 4-6 sentences describing the visual details and 1-2 audio-related descriptions at the end. The descriptions are provided in both English and Chinese. We create two new metrics for this task: an EntityScore to gauge the completeness of entities in the visual descriptions, and an AudioScore to assess the audio descriptions. As a preliminary approach to this task, we propose an audio-visual-language transformer that extends existing video captioning model with an additional audio branch. We combine the masked language modeling and auto-regressive language modeling losses to optimize our model so that it can produce paragraph-level descriptions. We illustrate the efficiency of our model in audio-visual-language modeling by evaluating it against the proposed benchmark using both conventional captioning metrics and our proposed metrics. We further put our benchmark to the test in video generation models, demonstrating that employing fine-grained video descriptions can create more intricate videos than using captions.

We introduce AuriStream, a biologically inspired model for encoding speech via a two-stage framework inspired by the human auditory processing hierarchy. The first stage transforms raw audio into a time-frequency representation based on the human cochlea, from which we extract discrete cochlear tokens. The second stage applies an autoregressive sequence model over the cochlear tokens. AuriStream learns meaningful phoneme and word representations, and state-of-the-art lexical semantics. AuriStream shows competitive performance on diverse downstream SUPERB speech tasks. Complementing AuriStream's strong representational capabilities, it generates continuations of audio which can be visualized in a spectrogram space and decoded back into audio, providing insights into the model's predictions. In summary, we present a two-stage framework for speech representation learning to advance the development of more human-like models that efficiently handle a range of speech-based tasks.

Self-supervised learning (SSL) has emerged as a popular approach for learning audio representations. One goal of audio self-supervised pre-training is to transfer knowledge to downstream audio tasks, generally including clip-level and frame-level tasks. While frame-level tasks are important for fine-grained acoustic scene/event understanding, prior studies primarily evaluate on clip-level downstream tasks. In order to tackle both clip-level and frame-level tasks, this paper proposes Audio Teacher-Student Transformer (ATST), with a clip-level version (named ATST-Clip) and a frame-level version (named ATST-Frame), responsible for learning clip-level and frame-level representations, respectively. Both methods use a Transformer encoder and a teacher-student training scheme. We have carefully designed the view creation strategy for ATST-Clip and ATST-Frame. Specifically, ATST-Clip uses segment-wise data augmentations, and ATST-Frame integrates frame-wise data augmentations and masking. Experimental results show that our ATST-Frame model obtains state-of-the-art (SOTA) performances on most of the clip-level and frame-level downstream tasks. Especially, it outperforms other models by a large margin on the frame-level sound event detection task. In addition, the performance can be further improved by combining the two models through knowledge distillation. Our code is available online.

Speech translation models are unable to directly process long audios, like TED talks, which have to be split into shorter segments. Speech translation datasets provide manual segmentations of the audios, which are not available in real-world scenarios, and existing segmentation methods usually significantly reduce translation quality at inference time. To bridge the gap between the manual segmentation of training and the automatic one at inference, we propose Supervised Hybrid Audio Segmentation (SHAS), a method that can effectively learn the optimal segmentation from any manually segmented speech corpus. First, we train a classifier to identify the included frames in a segmentation, using speech representations from a pre-trained wav2vec 2.0. The optimal splitting points are then found by a probabilistic Divide-and-Conquer algorithm that progressively splits at the frame of lowest probability until all segments are below a pre-specified length. Experiments on MuST-C and mTEDx show that the translation of the segments produced by our method approaches the quality of the manual segmentation on 5 language pairs. Namely, SHAS retains 95-98% of the manual segmentation's BLEU score, compared to the 87-93% of the best existing methods. Our method is additionally generalizable to different domains and achieves high zero-shot performance in unseen languages.

Most speech recognition tasks pertain to mapping words across two modalities: acoustic and orthographic. In this work, we suggest learning encoders that map variable-length, acoustic or phonetic, sequences that represent words into fixed-dimensional vectors in a shared latent space; such that the distance between two word vectors represents how closely the two words sound. Instead of directly learning the distances between word vectors, we employ weak supervision and model a binary classification task to predict whether two inputs, one of each modality, represent the same word given a distance threshold. We explore various deep-learning models, bimodal contrastive losses, and techniques for mining hard negative examples such as the semi-supervised technique of self-labeling. Our best model achieves an F_1 score of 0.95 for the binary classification task.

We consider the question: what can be learnt by looking at and listening to a large number of unlabelled videos? There is a valuable, but so far untapped, source of information contained in the video itself -- the correspondence between the visual and the audio streams, and we introduce a novel "Audio-Visual Correspondence" learning task that makes use of this. Training visual and audio networks from scratch, without any additional supervision other than the raw unconstrained videos themselves, is shown to successfully solve this task, and, more interestingly, result in good visual and audio representations. These features set the new state-of-the-art on two sound classification benchmarks, and perform on par with the state-of-the-art self-supervised approaches on ImageNet classification. We also demonstrate that the network is able to localize objects in both modalities, as well as perform fine-grained recognition tasks.

Speechreading is a notoriously difficult task for humans to perform. In this paper we present an end-to-end model based on a convolutional neural network (CNN) for generating an intelligible acoustic speech signal from silent video frames of a speaking person. The proposed CNN generates sound features for each frame based on its neighboring frames. Waveforms are then synthesized from the learned speech features to produce intelligible speech. We show that by leveraging the automatic feature learning capabilities of a CNN, we can obtain state-of-the-art word intelligibility on the GRID dataset, and show promising results for learning out-of-vocabulary (OOV) words.

Recent advances in neural text-to-speech research have been dominated by two-stage pipelines utilizing low-level intermediate speech representation such as mel-spectrograms. However, such predetermined features are fundamentally limited, because they do not allow to exploit the full potential of a data-driven approach through learning hidden representations. For this reason, several end-to-end methods have been proposed. However, such models are harder to train and require a large number of high-quality recordings with transcriptions. Here, we propose WavThruVec - a two-stage architecture that resolves the bottleneck by using high-dimensional Wav2Vec 2.0 embeddings as intermediate speech representation. Since these hidden activations provide high-level linguistic features, they are more robust to noise. That allows us to utilize annotated speech datasets of a lower quality to train the first-stage module. At the same time, the second-stage component can be trained on large-scale untranscribed audio corpora, as Wav2Vec 2.0 embeddings are already time-aligned. This results in an increased generalization capability to out-of-vocabulary words, as well as to a better generalization to unseen speakers. We show that the proposed model not only matches the quality of state-of-the-art neural models, but also presents useful properties enabling tasks like voice conversion or zero-shot synthesis.

The integration of audio perception capabilities into Large Language Models (LLMs) has enabled significant advances in Audio-LLMs. Although application-focused developments, particularly in curating training data for specific capabilities e.g., audio reasoning, have progressed rapidly, the underlying mechanisms that govern efficient transfer of rich semantic representations from audio encoders to LLMs remain under-explored. We conceptualize effective audio-LLM interaction as the LLM's ability to proficiently probe the audio encoder representations to satisfy textual queries. This paper presents a systematic investigation on how architectural design choices can affect that. Beginning with a standard Pengi/LLaVA-style audio-LLM architecture, we propose and evaluate several modifications guided by hypotheses derived from mechanistic interpretability studies and LLM operational principles. Our experiments demonstrate that: (1) delaying audio integration until the LLM's initial layers establish textual context that enhances its ability to probe the audio representations for relevant information; (2) the LLM can proficiently probe audio representations exclusively through LLM layer's attention submodule, without requiring propagation to its Feed-Forward Network (FFN) submodule; (3) an efficiently integrated ensemble of diverse audio encoders provides richer, complementary representations, thereby broadening the LLM's capacity to probe a wider spectrum of audio information. All hypotheses are evaluated using an identical three-stage training curriculum on a dataset of 5.6 million audio-text pairs, ensuring controlled comparisons. Our final architecture, which incorporates all proposed modifications, achieves relative improvements from 10\% to 60\% over the baseline, validating our approach to optimizing cross-modal information transfer in audio-LLMs. Project page: https://ta012.github.io/PAL/

Word embeddings that map words into a fixed-dimensional vector space are the backbone of modern NLP. Most word embedding methods encode semantic information. However, phonetic information, which is important for some tasks, is often overlooked. In this work, we develop several novel methods which leverage articulatory features to build phonetically informed word embeddings, and present a set of phonetic word embeddings to encourage their community development, evaluation and use. While several methods for learning phonetic word embeddings already exist, there is a lack of consistency in evaluating their effectiveness. Thus, we also proposes several ways to evaluate both intrinsic aspects of phonetic word embeddings, such as word retrieval and correlation with sound similarity, and extrinsic performances, such as rhyme and cognate detection and sound analogies. We hope that our suite of tasks will promote reproducibility and provide direction for future research on phonetic word embeddings.

In this paper we present an end-to-end speech recognition model with Transformer encoders that can be used in a streaming speech recognition system. Transformer computation blocks based on self-attention are used to encode both audio and label sequences independently. The activations from both audio and label encoders are combined with a feed-forward layer to compute a probability distribution over the label space for every combination of acoustic frame position and label history. This is similar to the Recurrent Neural Network Transducer (RNN-T) model, which uses RNNs for information encoding instead of Transformer encoders. The model is trained with the RNN-T loss well-suited to streaming decoding. We present results on the LibriSpeech dataset showing that limiting the left context for self-attention in the Transformer layers makes decoding computationally tractable for streaming, with only a slight degradation in accuracy. We also show that the full attention version of our model beats the-state-of-the art accuracy on the LibriSpeech benchmarks. Our results also show that we can bridge the gap between full attention and limited attention versions of our model by attending to a limited number of future frames.

We consider the task of generating diverse and realistic videos guided by natural audio samples from a wide variety of semantic classes. For this task, the videos are required to be aligned both globally and temporally with the input audio: globally, the input audio is semantically associated with the entire output video, and temporally, each segment of the input audio is associated with a corresponding segment of that video. We utilize an existing text-conditioned video generation model and a pre-trained audio encoder model. The proposed method is based on a lightweight adaptor network, which learns to map the audio-based representation to the input representation expected by the text-to-video generation model. As such, it also enables video generation conditioned on text, audio, and, for the first time as far as we can ascertain, on both text and audio. We validate our method extensively on three datasets demonstrating significant semantic diversity of audio-video samples and further propose a novel evaluation metric (AV-Align) to assess the alignment of generated videos with input audio samples. AV-Align is based on the detection and comparison of energy peaks in both modalities. In comparison to recent state-of-the-art approaches, our method generates videos that are better aligned with the input sound, both with respect to content and temporal axis. We also show that videos produced by our method present higher visual quality and are more diverse.

In recent years, large language models have achieved significant success in generative tasks (e.g., speech cloning and audio generation) related to speech, audio, music, and other signal domains. A crucial element of these models is the discrete acoustic codecs, which serves as an intermediate representation replacing the mel-spectrogram. However, there exist several gaps between discrete codecs and downstream speech language models. Specifically, 1) most codec models are trained on only 1,000 hours of data, whereas most speech language models are trained on 60,000 hours; 2) Achieving good reconstruction performance requires the utilization of numerous codebooks, which increases the burden on downstream speech language models; 3) The initial channel of the codebooks contains excessive information, making it challenging to directly generate acoustic tokens from weakly supervised signals such as text in downstream tasks. Consequently, leveraging the characteristics of speech language models, we propose Language-Codec. In the Language-Codec, we introduce a Mask Channel Residual Vector Quantization (MCRVQ) mechanism along with improved Fourier transform structures and larger training datasets to address the aforementioned gaps. We compare our method with competing audio compression algorithms and observe significant outperformance across extensive evaluations. Furthermore, we also validate the efficiency of the Language-Codec on downstream speech language models. The source code and pre-trained models can be accessed at https://github.com/jishengpeng/languagecodec .

We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech achieve 1.8/3.3 WER on the clean/other test sets. When lowering the amount of labeled data to one hour, wav2vec 2.0 outperforms the previous state of the art on the 100 hour subset while using 100 times less labeled data. Using just ten minutes of labeled data and pre-training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates the feasibility of speech recognition with limited amounts of labeled data.

How does audio describe the world around us? In this work, we propose a method for generating images of visual scenes from diverse in-the-wild sounds. This cross-modal generation task is challenging due to the significant information gap between auditory and visual signals. We address this challenge by designing a model that aligns audio-visual modalities by enriching audio features with visual information and translating them into the visual latent space. These features are then fed into the pre-trained image generator to produce images. To enhance image quality, we use sound source localization to select audio-visual pairs with strong cross-modal correlations. Our method achieves substantially better results on the VEGAS and VGGSound datasets compared to previous work and demonstrates control over the generation process through simple manipulations to the input waveform or latent space. Furthermore, we analyze the geometric properties of the learned embedding space and demonstrate that our learning approach effectively aligns audio-visual signals for cross-modal generation. Based on this analysis, we show that our method is agnostic to specific design choices, showing its generalizability by integrating various model architectures and different types of audio-visual data.

Lifelong audio feature extraction involves learning new sound classes incrementally, which is essential for adapting to new data distributions over time. However, optimizing the model only on new data can lead to catastrophic forgetting of previously learned tasks, which undermines the model's ability to perform well over the long term. This paper introduces a new approach to continual audio representation learning called DeCoR. Unlike other methods that store previous data, features, or models, DeCoR indirectly distills knowledge from an earlier model to the latest by predicting quantization indices from a delayed codebook. We demonstrate that DeCoR improves acoustic scene classification accuracy and integrates well with continual self-supervised representation learning. Our approach introduces minimal storage and computation overhead, making it a lightweight and efficient solution for continual learning.

We propose a new end-to-end neural acoustic model for automatic speech recognition. The model is composed of multiple blocks with residual connections between them. Each block consists of one or more modules with 1D time-channel separable convolutional layers, batch normalization, and ReLU layers. It is trained with CTC loss. The proposed network achieves near state-of-the-art accuracy on LibriSpeech and Wall Street Journal, while having fewer parameters than all competing models. We also demonstrate that this model can be effectively fine-tuned on new datasets.

Research on multi-modal contrastive learning strategies for audio and text has rapidly gained interest. Contrastively trained Audio-Language Models (ALMs), such as CLAP, which establish a unified representation across audio and language modalities, have enhanced the efficacy in various subsequent tasks by providing good text aligned audio encoders and vice versa. These improvements are evident in areas like zero-shot audio classification and audio retrieval, among others. However, the ability of these models to understand natural language and temporal relations is still a largely unexplored and open field for research. In this paper, we propose to equip the multi-modal ALMs with temporal understanding without loosing their inherent prior capabilities of audio-language tasks with a temporal instillation method TeminAL. We implement a two-stage training scheme TeminAL A & B, where the model first learns to differentiate between multiple sounds in TeminAL A, followed by a phase that instills a sense of time, thereby enhancing its temporal understanding in TeminAL B. This approach results in an average performance gain of 5.28% in temporal understanding on the ESC-50 dataset, while the model remains competitive in zero-shot retrieval and classification tasks on the AudioCap/Clotho datasets. We also note the lack of proper evaluation techniques for contrastive ALMs and propose a strategy for evaluating ALMs in zero-shot settings. The general-purpose zero-shot model evaluation strategy ZSTE, is used to evaluate various prior models. ZSTE demonstrates a general strategy to evaluate all ZS contrastive models. The model trained with TeminAL successfully outperforms current models on most downstream tasks.

We explore unsupervised pre-training for speech recognition by learning representations of raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting representations are then used to improve acoustic model training. We pre-train a simple multi-layer convolutional neural network optimized via a noise contrastive binary classification task. Our experiments on WSJ reduce WER of a strong character-based log-mel filterbank baseline by up to 36% when only a few hours of transcribed data is available. Our approach achieves 2.43% WER on the nov92 test set. This outperforms Deep Speech 2, the best reported character-based system in the literature while using two orders of magnitude less labeled training data.

This paper proposes to use low-level spatial features extracted from multichannel audio for sound event detection. We extend the convolutional recurrent neural network to handle more than one type of these multichannel features by learning from each of them separately in the initial stages. We show that instead of concatenating the features of each channel into a single feature vector the network learns sound events in multichannel audio better when they are presented as separate layers of a volume. Using the proposed spatial features over monaural features on the same network gives an absolute F-score improvement of 6.1% on the publicly available TUT-SED 2016 dataset and 2.7% on the TUT-SED 2009 dataset that is fifteen times larger.

In recent years, datasets of paired audio and captions have enabled remarkable success in automatically generating descriptions for audio clips, namely Automated Audio Captioning (AAC). However, it is labor-intensive and time-consuming to collect a sufficient number of paired audio and captions. Motivated by the recent advances in Contrastive Language-Audio Pretraining (CLAP), we propose a weakly-supervised approach to train an AAC model assuming only text data and a pre-trained CLAP model, alleviating the need for paired target data. Our approach leverages the similarity between audio and text embeddings in CLAP. During training, we learn to reconstruct the text from the CLAP text embedding, and during inference, we decode using the audio embeddings. To mitigate the modality gap between the audio and text embeddings we employ strategies to bridge the gap during training and inference stages. We evaluate our proposed method on Clotho and AudioCaps datasets demonstrating its ability to achieve a relative performance of up to ~83% compared to fully supervised approaches trained with paired target data.

While large language models (LLMs) have revolutionized text-to-speech (TTS) synthesis through discrete tokenization paradigms, current architectures exhibit fundamental tensions between three critical dimensions: 1) irreversible loss of acoustic characteristics caused by quantization of speech prompts; 2) stringent dependence on precisely aligned prompt speech-text pairs that limit real-world deployment; and 3) catastrophic forgetting of the LLM's native text comprehension during optimization for speech token generation. To address these challenges, we propose an LLM-based text-to-speech Generation approach Optimized via a novel dual-branch ArchiTecture (GOAT-TTS). Our framework introduces two key innovations: (1) The modality-alignment branch combines a speech encoder and projector to capture continuous acoustic embeddings, enabling bidirectional correlation between paralinguistic features (language, timbre, emotion) and semantic text representations without transcript dependency; (2) The speech-generation branch employs modular fine-tuning on top-k layers of an LLM for speech token prediction while freezing the bottom-k layers to preserve foundational linguistic knowledge. Moreover, multi-token prediction is introduced to support real-time streaming TTS synthesis. Experimental results demonstrate that our GOAT-TTS achieves performance comparable to state-of-the-art TTS models while validating the efficacy of synthesized dialect speech data.

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and languages for which only limited labeled data is available. Self-supervised representation learning methods promise a single universal model that would benefit a wide variety of tasks and domains. Such methods have shown success in natural language processing and computer vision domains, achieving new levels of performance while reducing the number of labels required for many downstream scenarios. Speech representation learning is experiencing similar progress in three main categories: generative, contrastive, and predictive methods. Other approaches rely on multi-modal data for pre-training, mixing text or visual data streams with speech. Although self-supervised speech representation is still a nascent research area, it is closely related to acoustic word embedding and learning with zero lexical resources, both of which have seen active research for many years. This review presents approaches for self-supervised speech representation learning and their connection to other research areas. Since many current methods focus solely on automatic speech recognition as a downstream task, we review recent efforts on benchmarking learned representations to extend the application beyond speech recognition.

Efficiently compressing high-dimensional audio signals into a compact and informative latent space is crucial for various tasks, including generative modeling and music information retrieval (MIR). Existing audio autoencoders, however, often struggle to achieve high compression ratios while preserving audio fidelity and facilitating efficient downstream applications. We introduce Music2Latent2, a novel audio autoencoder that addresses these limitations by leveraging consistency models and a novel approach to representation learning based on unordered latent embeddings, which we call summary embeddings. Unlike conventional methods that encode local audio features into ordered sequences, Music2Latent2 compresses audio signals into sets of summary embeddings, where each embedding can capture distinct global features of the input sample. This enables to achieve higher reconstruction quality at the same compression ratio. To handle arbitrary audio lengths, Music2Latent2 employs an autoregressive consistency model trained on two consecutive audio chunks with causal masking, ensuring coherent reconstruction across segment boundaries. Additionally, we propose a novel two-step decoding procedure that leverages the denoising capabilities of consistency models to further refine the generated audio at no additional cost. Our experiments demonstrate that Music2Latent2 outperforms existing continuous audio autoencoders regarding audio quality and performance on downstream tasks. Music2Latent2 paves the way for new possibilities in audio compression.

Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose instead to learn such embeddings from video data with readily available natural language annotations in the form of automatically transcribed narrations. The contributions of this work are three-fold. First, we introduce HowTo100M: a large-scale dataset of 136 million video clips sourced from 1.22M narrated instructional web videos depicting humans performing and describing over 23k different visual tasks. Our data collection procedure is fast, scalable and does not require any additional manual annotation. Second, we demonstrate that a text-video embedding trained on this data leads to state-of-the-art results for text-to-video retrieval and action localization on instructional video datasets such as YouCook2 or CrossTask. Finally, we show that this embedding transfers well to other domains: fine-tuning on generic Youtube videos (MSR-VTT dataset) and movies (LSMDC dataset) outperforms models trained on these datasets alone. Our dataset, code and models will be publicly available at: www.di.ens.fr/willow/research/howto100m/.

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test sets from the same dataset. Such methods have two limitations. First, these methods are often data-hungry and require time-consuming and expensive human annotations to obtain audio-text pairs. Second, these models often suffer from performance degradation in cross-domain scenarios, i.e., when the input audio comes from a different domain than the training set, which, however, has received little attention. We propose an effective audio captioning method based on the contrastive language-audio pre-training (CLAP) model to address these issues. Our proposed method requires only textual data for training, enabling the model to generate text from the textual feature in the cross-modal semantic space.In the inference stage, the model generates the descriptive text for the given audio from the audio feature by leveraging the audio-text alignment from CLAP.We devise two strategies to mitigate the discrepancy between text and audio embeddings: a mixed-augmentation-based soft prompt and a retrieval-based acoustic-aware hard prompt. These approaches are designed to enhance the generalization performance of our proposed model, facilitating the model to generate captions more robustly and accurately. Extensive experiments on AudioCaps and Clotho benchmarks show the effectiveness of our proposed method, which outperforms other zero-shot audio captioning approaches for in-domain scenarios and outperforms the compared methods for cross-domain scenarios, underscoring the generalization ability of our method.

The goal of this work is to train strong models for visual speech recognition without requiring human annotated ground truth data. We achieve this by distilling from an Automatic Speech Recognition (ASR) model that has been trained on a large-scale audio-only corpus. We use a cross-modal distillation method that combines Connectionist Temporal Classification (CTC) with a frame-wise cross-entropy loss. Our contributions are fourfold: (i) we show that ground truth transcriptions are not necessary to train a lip reading system; (ii) we show how arbitrary amounts of unlabelled video data can be leveraged to improve performance; (iii) we demonstrate that distillation significantly speeds up training; and, (iv) we obtain state-of-the-art results on the challenging LRS2 and LRS3 datasets for training only on publicly available data.

Neural text-to-speech (TTS) has achieved human-like synthetic speech for single-speaker, single-language synthesis. Multilingual TTS systems are limited to resource-rich languages due to the lack of large paired text and studio-quality audio data. In most cases, TTS systems are built using a single speaker's voice. However, there is growing interest in developing systems that can synthesize voices for new speakers using only a few seconds of their speech. This paper presents ZMM-TTS, a multilingual and multispeaker framework utilizing quantized latent speech representations from a large-scale, pre-trained, self-supervised model. Our paper is the first to incorporate the representations from text-based and speech-based self-supervised learning models into multilingual speech synthesis tasks. We conducted comprehensive subjective and objective evaluations through a series of experiments. Our model has been proven effective in terms of speech naturalness and similarity for both seen and unseen speakers in six high-resource languages. We also tested the efficiency of our method on two hypothetical low-resource languages. The results are promising, indicating that our proposed approach can synthesize audio that is intelligible and has a high degree of similarity to the target speaker's voice, even without any training data for the new, unseen language.

We propose and investigate an identity sensitive joint embedding of face and voice. Such an embedding enables cross-modal retrieval from voice to face and from face to voice. We make the following four contributions: first, we show that the embedding can be learnt from videos of talking faces, without requiring any identity labels, using a form of cross-modal self-supervision; second, we develop a curriculum learning schedule for hard negative mining targeted to this task, that is essential for learning to proceed successfully; third, we demonstrate and evaluate cross-modal retrieval for identities unseen and unheard during training over a number of scenarios and establish a benchmark for this novel task; finally, we show an application of using the joint embedding for automatically retrieving and labelling characters in TV dramas.

Despite significant advancements in neural text-to-audio generation, challenges persist in controllability and evaluation. This paper addresses these issues through the Sound Scene Synthesis challenge held as part of the Detection and Classification of Acoustic Scenes and Events 2024. We present an evaluation protocol combining objective metric, namely Fr\'echet Audio Distance, with perceptual assessments, utilizing a structured prompt format to enable diverse captions and effective evaluation. Our analysis reveals varying performance across sound categories and model architectures, with larger models generally excelling but innovative lightweight approaches also showing promise. The strong correlation between objective metrics and human ratings validates our evaluation approach. We discuss outcomes in terms of audio quality, controllability, and architectural considerations for text-to-audio synthesizers, providing direction for future research.

With the emergence of neural audio codecs, which encode multiple streams of discrete tokens from audio, large language models have recently gained attention as a promising approach for zero-shot Text-to-Speech (TTS) synthesis. Despite the ongoing rush towards scaling paradigms, audio tokenization ironically amplifies the scalability challenge, stemming from its long sequence length and the complexity of modelling the multiple sequences. To mitigate these issues, we present CLaM-TTS that employs a probabilistic residual vector quantization to (1) achieve superior compression in the token length, and (2) allow a language model to generate multiple tokens at once, thereby eliminating the need for cascaded modeling to handle the number of token streams. Our experimental results demonstrate that CLaM-TTS is better than or comparable to state-of-the-art neural codec-based TTS models regarding naturalness, intelligibility, speaker similarity, and inference speed. In addition, we examine the impact of the pretraining extent of the language models and their text tokenization strategies on performances.

Integrating multiple generative foundation models, especially those trained on different modalities, into something greater than the sum of its parts poses significant challenges. Two key hurdles are the availability of aligned data (concepts that contain similar meaning but is expressed differently in different modalities), and effectively leveraging unimodal representations in cross-domain generative tasks, without compromising their original unimodal capabilities. We propose Zipper, a multi-tower decoder architecture that addresses these concerns by using cross-attention to flexibly compose multimodal generative models from independently pre-trained unimodal decoders. In our experiments fusing speech and text modalities, we show the proposed architecture performs very competitively in scenarios with limited aligned text-speech data. We also showcase the flexibility of our model to selectively maintain unimodal (e.g., text-to-text generation) generation performance by freezing the corresponding modal tower (e.g. text). In cross-modal tasks such as automatic speech recognition (ASR) where the output modality is text, we show that freezing the text backbone results in negligible performance degradation. In cross-modal tasks such as text-to-speech generation (TTS) where the output modality is speech, we show that using a pre-trained speech backbone results in superior performance to the baseline.

Recently, the end-to-end approach that learns hierarchical representations from raw data using deep convolutional neural networks has been successfully explored in the image, text and speech domains. This approach was applied to musical signals as well but has been not fully explored yet. To this end, we propose sample-level deep convolutional neural networks which learn representations from very small grains of waveforms (e.g. 2 or 3 samples) beyond typical frame-level input representations. Our experiments show how deep architectures with sample-level filters improve the accuracy in music auto-tagging and they provide results comparable to previous state-of-the-art performances for the Magnatagatune dataset and Million Song Dataset. In addition, we visualize filters learned in a sample-level DCNN in each layer to identify hierarchically learned features and show that they are sensitive to log-scaled frequency along layer, such as mel-frequency spectrogram that is widely used in music classification systems.

Learning to localize the sound source in videos without explicit annotations is a novel area of audio-visual research. Existing work in this area focuses on creating attention maps to capture the correlation between the two modalities to localize the source of the sound. In a video, oftentimes, the objects exhibiting movement are the ones generating the sound. In this work, we capture this characteristic by modeling the optical flow in a video as a prior to better aid in localizing the sound source. We further demonstrate that the addition of flow-based attention substantially improves visual sound source localization. Finally, we benchmark our method on standard sound source localization datasets and achieve state-of-the-art performance on the Soundnet Flickr and VGG Sound Source datasets. Code: https://github.com/denfed/heartheflow.

Conditional sound separation in multi-source audio mixtures without having access to single source sound data during training is a long standing challenge. Existing mix-and-separate based methods suffer from significant performance drop with multi-source training mixtures due to the lack of supervision signal for single source separation cases during training. However, in the case of language-conditional audio separation, we do have access to corresponding text descriptions for each audio mixture in our training data, which can be seen as (rough) representations of the audio samples in the language modality. To this end, in this paper, we propose a generic bi-modal separation framework which can enhance the existing unsupervised frameworks to separate single-source signals in a target modality (i.e., audio) using the easily separable corresponding signals in the conditioning modality (i.e., language), without having access to single-source samples in the target modality during training. We empirically show that this is well within reach if we have access to a pretrained joint embedding model between the two modalities (i.e., CLAP). Furthermore, we propose to incorporate our framework into two fundamental scenarios to enhance separation performance. First, we show that our proposed methodology significantly improves the performance of purely unsupervised baselines by reducing the distribution shift between training and test samples. In particular, we show that our framework can achieve 71% boost in terms of Signal-to-Distortion Ratio (SDR) over the baseline, reaching 97.5% of the supervised learning performance. Second, we show that we can further improve the performance of the supervised learning itself by 17% if we augment it by our proposed weakly-supervised framework, that enables a powerful semi-supervised framework for audio separation.

Scaling text-to-speech to a large and wild dataset has been proven to be highly effective in achieving timbre and speech style generalization, particularly in zero-shot TTS. However, previous works usually encode speech into latent using audio codec and use autoregressive language models or diffusion models to generate it, which ignores the intrinsic nature of speech and may lead to inferior or uncontrollable results. We argue that speech can be decomposed into several attributes (e.g., content, timbre, prosody, and phase) and each of them should be modeled using a module with appropriate inductive biases. From this perspective, we carefully design a novel and large zero-shot TTS system called Mega-TTS, which is trained with large-scale wild data and models different attributes in different ways: 1) Instead of using latent encoded by audio codec as the intermediate feature, we still choose spectrogram as it separates the phase and other attributes very well. Phase can be appropriately constructed by the GAN-based vocoder and does not need to be modeled by the language model. 2) We model the timbre using global vectors since timbre is a global attribute that changes slowly over time. 3) We further use a VQGAN-based acoustic model to generate the spectrogram and a latent code language model to fit the distribution of prosody, since prosody changes quickly over time in a sentence, and language models can capture both local and long-range dependencies. We scale Mega-TTS to multi-domain datasets with 20K hours of speech and evaluate its performance on unseen speakers. Experimental results demonstrate that Mega-TTS surpasses state-of-the-art TTS systems on zero-shot TTS, speech editing, and cross-lingual TTS tasks, with superior naturalness, robustness, and speaker similarity due to the proper inductive bias of each module. Audio samples are available at https://mega-tts.github.io/demo-page.

Generating semantically and temporally aligned audio content in accordance with video input has become a focal point for researchers, particularly following the remarkable breakthrough in text-to-video generation. In this work, we aim to offer insights into the video-to-audio generation paradigm, focusing on three crucial aspects: vision encoders, auxiliary embeddings, and data augmentation techniques. Beginning with a foundational model VTA-LDM built on a simple yet surprisingly effective intuition, we explore various vision encoders and auxiliary embeddings through ablation studies. Employing a comprehensive evaluation pipeline that emphasizes generation quality and video-audio synchronization alignment, we demonstrate that our model exhibits state-of-the-art video-to-audio generation capabilities. Furthermore, we provide critical insights into the impact of different data augmentation methods on enhancing the generation framework's overall capacity. We showcase possibilities to advance the challenge of generating synchronized audio from semantic and temporal perspectives. We hope these insights will serve as a stepping stone toward developing more realistic and accurate audio-visual generation models.

Lyrics alignment gained considerable attention in recent years. State-of-the-art systems either re-use established speech recognition toolkits, or design end-to-end solutions involving a Connectionist Temporal Classification (CTC) loss. However, both approaches suffer from specific weaknesses: toolkits are known for their complexity, and CTC systems use a loss designed for transcription which can limit alignment accuracy. In this paper, we use instead a contrastive learning procedure that derives cross-modal embeddings linking the audio and text domains. This way, we obtain a novel system that is simple to train end-to-end, can make use of weakly annotated training data, jointly learns a powerful text model, and is tailored to alignment. The system is not only the first to yield an average absolute error below 0.2 seconds on the standard Jamendo dataset but it is also robust to other languages, even when trained on English data only. Finally, we release word-level alignments for the JamendoLyrics Multi-Lang dataset.

In this study, we present a simple multi-channel framework for contrastive learning (MC-SimCLR) to encode 'what' and 'where' of spatial audios. MC-SimCLR learns joint spectral and spatial representations from unlabeled spatial audios, thereby enhancing both event classification and sound localization in downstream tasks. At its core, we propose a multi-level data augmentation pipeline that augments different levels of audio features, including waveforms, Mel spectrograms, and generalized cross-correlation (GCC) features. In addition, we introduce simple yet effective channel-wise augmentation methods to randomly swap the order of the microphones and mask Mel and GCC channels. By using these augmentations, we find that linear layers on top of the learned representation significantly outperform supervised models in terms of both event classification accuracy and localization error. We also perform a comprehensive analysis of the effect of each augmentation method and a comparison of the fine-tuning performance using different amounts of labeled data.

Text-to-audio grounding (TAG) task aims to predict the onsets and offsets of sound events described by natural language. This task can facilitate applications such as multimodal information retrieval. This paper focuses on weakly-supervised text-to-audio grounding (WSTAG), where frame-level annotations of sound events are unavailable, and only the caption of a whole audio clip can be utilized for training. WSTAG is superior to strongly-supervised approaches in its scalability to large audio-text datasets. Two WSTAG frameworks are studied in this paper: sentence-level and phrase-level. First, we analyze the limitations of mean pooling used in the previous WSTAG approach and investigate the effects of different pooling strategies. We then propose phrase-level WSTAG to use matching labels between audio clips and phrases for training. Advanced negative sampling strategies and self-supervision are proposed to enhance the accuracy of the weak labels and provide pseudo strong labels. Experimental results show that our system significantly outperforms the previous WSTAG SOTA. Finally, we conduct extensive experiments to analyze the effects of several factors on phrase-level WSTAG. The code and model is available at https://github.com/wsntxxn/TextToAudioGrounding.

Recent research has demonstrated impressive results in video-to-speech synthesis which involves reconstructing speech solely from visual input. However, previous works have struggled to accurately synthesize speech due to a lack of sufficient guidance for the model to infer the correct content with the appropriate sound. To resolve the issue, they have adopted an extra speaker embedding as a speaking style guidance from a reference auditory information. Nevertheless, it is not always possible to obtain the audio information from the corresponding video input, especially during the inference time. In this paper, we present a novel vision-guided speaker embedding extractor using a self-supervised pre-trained model and prompt tuning technique. In doing so, the rich speaker embedding information can be produced solely from input visual information, and the extra audio information is not necessary during the inference time. Using the extracted vision-guided speaker embedding representations, we further develop a diffusion-based video-to-speech synthesis model, so called DiffV2S, conditioned on those speaker embeddings and the visual representation extracted from the input video. The proposed DiffV2S not only maintains phoneme details contained in the input video frames, but also creates a highly intelligible mel-spectrogram in which the speaker identities of the multiple speakers are all preserved. Our experimental results show that DiffV2S achieves the state-of-the-art performance compared to the previous video-to-speech synthesis technique.

Despite recent progress in text-to-audio (TTA) generation, we show that the state-of-the-art models, such as AudioLDM, trained on datasets with an imbalanced class distribution, such as AudioCaps, are biased in their generation performance. Specifically, they excel in generating common audio classes while underperforming in the rare ones, thus degrading the overall generation performance. We refer to this problem as long-tailed text-to-audio generation. To address this issue, we propose a simple retrieval-augmented approach for TTA models. Specifically, given an input text prompt, we first leverage a Contrastive Language Audio Pretraining (CLAP) model to retrieve relevant text-audio pairs. The features of the retrieved audio-text data are then used as additional conditions to guide the learning of TTA models. We enhance AudioLDM with our proposed approach and denote the resulting augmented system as Re-AudioLDM. On the AudioCaps dataset, Re-AudioLDM achieves a state-of-the-art Frechet Audio Distance (FAD) of 1.37, outperforming the existing approaches by a large margin. Furthermore, we show that Re-AudioLDM can generate realistic audio for complex scenes, rare audio classes, and even unseen audio types, indicating its potential in TTA tasks.

Time-aligned lyrics can enrich the music listening experience by enabling karaoke, text-based song retrieval and intra-song navigation, and other applications. Compared to text-to-speech alignment, lyrics alignment remains highly challenging, despite many attempts to combine numerous sub-modules including vocal separation and detection in an effort to break down the problem. Furthermore, training required fine-grained annotations to be available in some form. Here, we present a novel system based on a modified Wave-U-Net architecture, which predicts character probabilities directly from raw audio using learnt multi-scale representations of the various signal components. There are no sub-modules whose interdependencies need to be optimized. Our training procedure is designed to work with weak, line-level annotations available in the real world. With a mean alignment error of 0.35s on a standard dataset our system outperforms the state-of-the-art by an order of magnitude.

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages, utilizing discrete semantic tokens obtained from wav2vec2.0 embeddings. For a robust and efficient alignment modeling, we employ a neural transducer named token transducer for the semantic token prediction, benefiting from its hard monotonic alignment constraints. Subsequently, a non-autoregressive (NAR) speech generator efficiently synthesizes waveforms from these semantic tokens. Additionally, a reference speech controls temporal dynamics and acoustic conditions at each stage. This decoupled framework reduces the training complexity of TTS while allowing each stage to focus on semantic and acoustic modeling. Our experimental results on zero-shot adaptive TTS demonstrate that our model surpasses the baseline in terms of speech quality and speaker similarity, both objectively and subjectively. We also delve into the inference speed and prosody control capabilities of our approach, highlighting the potential of neural transducers in TTS frameworks.

Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling techniques to audio data. However, audio codecs often operate at high frame rates, resulting in slow training and inference, especially for autoregressive models. To address this challenge, we present the Low Frame-rate Speech Codec (LFSC): a neural audio codec that leverages finite scalar quantization and adversarial training with large speech language models to achieve high-quality audio compression with a 1.89 kbps bitrate and 21.5 frames per second. We demonstrate that our novel codec can make the inference of LLM-based text-to-speech models around three times faster while improving intelligibility and producing quality comparable to previous models.

Recent work has studied text-to-audio synthesis using large amounts of paired text-audio data. However, audio recordings with high-quality text annotations can be difficult to acquire. In this work, we approach text-to-audio synthesis using unlabeled videos and pretrained language-vision models. We propose to learn the desired text-audio correspondence by leveraging the visual modality as a bridge. We train a conditional diffusion model to generate the audio track of a video, given a video frame encoded by a pretrained contrastive language-image pretraining (CLIP) model. At test time, we first explore performing a zero-shot modality transfer and condition the diffusion model with a CLIP-encoded text query. However, we observe a noticeable performance drop with respect to image queries. To close this gap, we further adopt a pretrained diffusion prior model to generate a CLIP image embedding given a CLIP text embedding. Our results show the effectiveness of the proposed method, and that the pretrained diffusion prior can reduce the modality transfer gap. While we focus on text-to-audio synthesis, the proposed model can also generate audio from image queries, and it shows competitive performance against a state-of-the-art image-to-audio synthesis model in a subjective listening test. This study offers a new direction of approaching text-to-audio synthesis that leverages the naturally-occurring audio-visual correspondence in videos and the power of pretrained language-vision models.

We propose vq-wav2vec to learn discrete representations of audio segments through a wav2vec-style self-supervised context prediction task. The algorithm uses either a gumbel softmax or online k-means clustering to quantize the dense representations. Discretization enables the direct application of algorithms from the NLP community which require discrete inputs. Experiments show that BERT pre-training achieves a new state of the art on TIMIT phoneme classification and WSJ speech recognition.

We propose a new problem called audio-visual segmentation (AVS), in which the goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame. To facilitate this research, we construct the first audio-visual segmentation benchmark, i.e., AVSBench, providing pixel-wise annotations for sounding objects in audible videos. It contains three subsets: AVSBench-object (Single-source subset, Multi-sources subset) and AVSBench-semantic (Semantic-labels subset). Accordingly, three settings are studied: 1) semi-supervised audio-visual segmentation with a single sound source; 2) fully-supervised audio-visual segmentation with multiple sound sources, and 3) fully-supervised audio-visual semantic segmentation. The first two settings need to generate binary masks of sounding objects indicating pixels corresponding to the audio, while the third setting further requires generating semantic maps indicating the object category. To deal with these problems, we propose a new baseline method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process. We also design a regularization loss to encourage audio-visual mapping during training. Quantitative and qualitative experiments on AVSBench compare our approach to several existing methods for related tasks, demonstrating that the proposed method is promising for building a bridge between the audio and pixel-wise visual semantics. Code is available at https://github.com/OpenNLPLab/AVSBench. Online benchmark is available at http://www.avlbench.opennlplab.cn.

Self-supervised learning (SSL) speech models such as wav2vec and HuBERT have demonstrated state-of-the-art performance on automatic speech recognition (ASR) and proved to be extremely useful in low label-resource settings. However, the success of SSL models has yet to transfer to utterance-level tasks such as speaker, emotion, and language recognition, which still require supervised fine-tuning of the SSL models to obtain good performance. We argue that the problem is caused by the lack of disentangled representations and an utterance-level learning objective for these tasks. Inspired by how HuBERT uses clustering to discover hidden acoustic units, we formulate a factor analysis (FA) model that uses the discovered hidden acoustic units to align the SSL features. The underlying utterance-level representations are disentangled from the content of speech using probabilistic inference on the aligned features. Furthermore, the variational lower bound derived from the FA model provides an utterance-level objective, allowing error gradients to be backpropagated to the Transformer layers to learn highly discriminative acoustic units. When used in conjunction with HuBERT's masked prediction training, our models outperform the current best model, WavLM, on all utterance-level non-semantic tasks on the SUPERB benchmark with only 20% of labeled data.

We present Video-LLaMA, a multi-modal framework that empowers Large Language Models (LLMs) with the capability of understanding both visual and auditory content in the video. Video-LLaMA bootstraps cross-modal training from the frozen pre-trained visual \& audio encoders and the frozen LLMs. Unlike previous vision- LLMs that focus on static image comprehensions such as MiniGPT-4~zhu2023minigpt and LLaVA~liu2023visualit, Video-LLaMA tackles two challenges in video understanding: (1) capturing the temporal changes in visual scenes, (2) integrating audio-visual signals. For the first challenge, we propose Video Q-former to extend the pre-trained image encoder to a video encoder and introduce a video-to-text generation task to learn video-language correspondence. For the second challenge, we leverage ImageBind~girdhar2023imagebind as the pre-trained audio encoder which performs exceptionally well in aligning different modalities to a common embedding space. And then introduce an Audio Q-former to learn auditory query tokens. To align the output of both visual \& audio encoder with LLM's embedding space, we train Video-LLaMA on a large-scale vision caption dataset and a hign-quantity vision-instruction-tuning dataset. We found Video-LLaMA showcases the ability to perceive and comprehend video content, generating meaningful responses that are grounded in the visual and auditory information present in the videos. This highlights the potential of Video-LLaMA as a promising prototype for audio-visual AI assistants. Our code, pre-trained model, and demo are available at https://github.com/DAMO-NLP-SG/Video-LLaMA.

Contrastive learning has shown remarkable success in the field of multimodal representation learning. In this paper, we propose a pipeline of contrastive language-audio pretraining to develop an audio representation by combining audio data with natural language descriptions. To accomplish this target, we first release LAION-Audio-630K, a large collection of 633,526 audio-text pairs from different data sources. Second, we construct a contrastive language-audio pretraining model by considering different audio encoders and text encoders. We incorporate the feature fusion mechanism and keyword-to-caption augmentation into the model design to further enable the model to process audio inputs of variable lengths and enhance the performance. Third, we perform comprehensive experiments to evaluate our model across three tasks: text-to-audio retrieval, zero-shot audio classification, and supervised audio classification. The results demonstrate that our model achieves superior performance in text-to-audio retrieval task. In audio classification tasks, the model achieves state-of-the-art performance in the zero-shot setting and is able to obtain performance comparable to models' results in the non-zero-shot setting. LAION-Audio-630K and the proposed model are both available to the public.

This paper presents a way of doing large scale audio understanding without traditional state of the art neural architectures. Ever since the introduction of deep learning for understanding audio signals in the past decade, convolutional architectures have been able to achieve state of the art results surpassing traditional hand-crafted features. In the recent past, there has been a similar shift away from traditional convolutional and recurrent neural networks towards purely end-to-end Transformer architectures. We, in this work, explore an approach, based on Bag-of-Words model. Our approach does not have any convolutions, recurrence, attention, transformers or other approaches such as BERT. We utilize micro and macro level clustered vanilla embeddings, and use a MLP head for classification. We only use feed-forward encoder-decoder models to get the bottlenecks of spectral envelops, spectral patches and slices as well as multi-resolution spectra. A classification head (a feed-forward layer), similar to the approach in SimCLR is trained on a learned representation. Using simple codes learned on latent representations, we show how we surpass traditional convolutional neural network architectures, and come strikingly close to outperforming powerful Transformer architectures. This work hopefully would pave way for exciting advancements in the field of representation learning without massive, end-to-end neural architectures.

Our environment is filled with rich and dynamic acoustic information. When we walk into a cathedral, the reverberations as much as appearance inform us of the sanctuary's wide open space. Similarly, as an object moves around us, we expect the sound emitted to also exhibit this movement. While recent advances in learned implicit functions have led to increasingly higher quality representations of the visual world, there have not been commensurate advances in learning spatial auditory representations. To address this gap, we introduce Neural Acoustic Fields (NAFs), an implicit representation that captures how sounds propagate in a physical scene. By modeling acoustic propagation in a scene as a linear time-invariant system, NAFs learn to continuously map all emitter and listener location pairs to a neural impulse response function that can then be applied to arbitrary sounds. We demonstrate that the continuous nature of NAFs enables us to render spatial acoustics for a listener at an arbitrary location, and can predict sound propagation at novel locations. We further show that the representation learned by NAFs can help improve visual learning with sparse views. Finally, we show that a representation informative of scene structure emerges during the learning of NAFs.

In the domain of audio processing, Transfer Learning has facilitated the rise of Self-Supervised Learning and Zero-Shot Learning techniques. These approaches have led to the development of versatile models capable of tackling a wide array of tasks, while delivering state-of-the-art performance. However, current models inherently lack the capacity to produce the requisite language for open-ended tasks, such as Audio Captioning or Audio Question & Answering. We introduce Pengi, a novel Audio Language Model that leverages Transfer Learning by framing all audio tasks as text-generation tasks. It takes as input, an audio recording, and text, and generates free-form text as output. The input audio is represented as a sequence of continuous embeddings by an audio encoder. A text encoder does the same for the corresponding text input. Both sequences are combined as a prefix to prompt a pre-trained frozen language model. The unified architecture of Pengi enables open-ended tasks and close-ended tasks without any additional fine-tuning or task-specific extensions. When evaluated on 22 downstream tasks, our approach yields state-of-the-art performance in several of them. Our results show that connecting language models with audio models is a major step towards general-purpose audio understanding

Many applications of cross-modal music retrieval are related to connecting sheet music images to audio recordings. A typical and recent approach to this is to learn, via deep neural networks, a joint embedding space that correlates short fixed-size snippets of audio and sheet music by means of an appropriate similarity structure. However, two challenges that arise out of this strategy are the requirement of strongly aligned data to train the networks, and the inherent discrepancies of musical content between audio and sheet music snippets caused by local and global tempo differences. In this paper, we address these two shortcomings by designing a cross-modal recurrent network that learns joint embeddings that can summarize longer passages of corresponding audio and sheet music. The benefits of our method are that it only requires weakly aligned audio-sheet music pairs, as well as that the recurrent network handles the non-linearities caused by tempo variations between audio and sheet music. We conduct a number of experiments on synthetic and real piano data and scores, showing that our proposed recurrent method leads to more accurate retrieval in all possible configurations.

This work explores whether language models encode meaningfully grounded representations of sounds of objects. We learn a linear probe that retrieves the correct text representation of an object given a snippet of audio related to that object, where the sound representation is given by a pretrained audio model. This probe is trained via a contrastive loss that pushes the language representations and sound representations of an object to be close to one another. After training, the probe is tested on its ability to generalize to objects that were not seen during training. Across different language models and audio models, we find that the probe generalization is above chance in many cases, indicating that despite being trained only on raw text, language models encode grounded knowledge of sounds for some objects.

Large audio-video language models can generate descriptions for both video and audio. However, they sometimes ignore audio content, producing audio descriptions solely reliant on visual information. This paper refers to this as audio hallucinations and analyzes them in large audio-video language models. We gather 1,000 sentences by inquiring about audio information and annotate them whether they contain hallucinations. If a sentence is hallucinated, we also categorize the type of hallucination. The results reveal that 332 sentences are hallucinated with distinct trends observed in nouns and verbs for each hallucination type. Based on this, we tackle a task of audio hallucination classification using pre-trained audio-text models in the zero-shot and fine-tuning settings. Our experimental results reveal that the zero-shot models achieve higher performance (52.2% in F1) than the random (40.3%) and the fine-tuning models achieve 87.9%, outperforming the zero-shot models.

Recent approaches to improving the extraction of text embeddings from autoregressive large language models (LLMs) have largely focused on improvements to data, backbone pretrained language models, or improving task-differentiation via instructions. In this work, we address an architectural limitation of autoregressive models: token embeddings cannot contain information from tokens that appear later in the input. To address this limitation, we propose a simple approach, "echo embeddings," in which we repeat the input twice in context and extract embeddings from the second occurrence. We show that echo embeddings of early tokens can encode information about later tokens, allowing us to maximally leverage high-quality LLMs for embeddings. On the MTEB leaderboard, echo embeddings improve over classical embeddings by over 9% zero-shot and by around 0.7% when fine-tuned. Echo embeddings with a Mistral-7B model achieve state-of-the-art compared to prior open source models that do not leverage synthetic fine-tuning data.

Syllables are compositional units of spoken language that play a crucial role in human speech perception and production. However, current neural speech representations lack structure, resulting in dense token sequences that are costly to process. To bridge this gap, we propose a new model, Sylber, that produces speech representations with clean and robust syllabic structure. Specifically, we propose a self-supervised model that regresses features on syllabic segments distilled from a teacher model which is an exponential moving average of the model in training. This results in a highly structured representation of speech features, offering three key benefits: 1) a fast, linear-time syllable segmentation algorithm, 2) efficient syllabic tokenization with an average of 4.27 tokens per second, and 3) syllabic units better suited for lexical and syntactic understanding. We also train token-to-speech generative models with our syllabic units and show that fully intelligible speech can be reconstructed from these tokens. Lastly, we observe that categorical perception, a linguistic phenomenon of speech perception, emerges naturally in our model, making the embedding space more categorical and sparse than previous self-supervised learning approaches. Together, we present a novel self-supervised approach for representing speech as syllables, with significant potential for efficient speech tokenization and spoken language modeling.

The objective of this paper is to learn representations of speaker identity without access to manually annotated data. To do so, we develop a self-supervised learning objective that exploits the natural cross-modal synchrony between faces and audio in video. The key idea behind our approach is to tease apart--without annotation--the representations of linguistic content and speaker identity. We construct a two-stream architecture which: (1) shares low-level features common to both representations; and (2) provides a natural mechanism for explicitly disentangling these factors, offering the potential for greater generalisation to novel combinations of content and identity and ultimately producing speaker identity representations that are more robust. We train our method on a large-scale audio-visual dataset of talking heads `in the wild', and demonstrate its efficacy by evaluating the learned speaker representations for standard speaker recognition performance.

We introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of metrics to automatically evaluate the learned representations at acoustic and linguistic levels for both encoding and generation. We set up baseline systems consisting of a discrete speech encoder (returning pseudo-text units), a generative language model (trained on pseudo-text), and a speech decoder (generating a waveform from pseudo-text) all trained without supervision and validate the proposed metrics with human evaluation. Across 3 speech encoders (CPC, wav2vec 2.0, HuBERT), we find that the number of discrete units (50, 100, or 200) matters in a task-dependent and encoder-dependent way, and that some combinations approach text-based systems.

Modeling temporal characteristics plays a significant role in the representation learning of audio waveform. We propose Contrastive Long-form Language-Audio Pretraining (CoLLAP) to significantly extend the perception window for both the input audio (up to 5 minutes) and the language descriptions (exceeding 250 words), while enabling contrastive learning across modalities and temporal dynamics. Leveraging recent Music-LLMs to generate long-form music captions for full-length songs, augmented with musical temporal structures, we collect 51.3K audio-text pairs derived from the large-scale AudioSet training dataset, where the average audio length reaches 288 seconds. We propose a novel contrastive learning architecture that fuses language representations with structured audio representations by segmenting each song into clips and extracting their embeddings. With an attention mechanism, we capture multimodal temporal correlations, allowing the model to automatically weigh and enhance the final fusion score for improved contrastive alignment. Finally, we develop two variants of the CoLLAP model with different types of backbone language models. Through comprehensive experiments on multiple long-form music-text retrieval datasets, we demonstrate consistent performance improvement in retrieval accuracy compared with baselines. We also show the pretrained CoLLAP models can be transferred to various music information retrieval tasks, with heterogeneous long-form multimodal contexts.

Recent years have seen progress beyond domain-specific sound separation for speech or music towards universal sound separation for arbitrary sounds. Prior work on universal sound separation has investigated separating a target sound out of an audio mixture given a text query. Such text-queried sound separation systems provide a natural and scalable interface for specifying arbitrary target sounds. However, supervised text-queried sound separation systems require costly labeled audio-text pairs for training. Moreover, the audio provided in existing datasets is often recorded in a controlled environment, causing a considerable generalization gap to noisy audio in the wild. In this work, we aim to approach text-queried universal sound separation by using only unlabeled data. We propose to leverage the visual modality as a bridge to learn the desired audio-textual correspondence. The proposed CLIPSep model first encodes the input query into a query vector using the contrastive language-image pretraining (CLIP) model, and the query vector is then used to condition an audio separation model to separate out the target sound. While the model is trained on image-audio pairs extracted from unlabeled videos, at test time we can instead query the model with text inputs in a zero-shot setting, thanks to the joint language-image embedding learned by the CLIP model. Further, videos in the wild often contain off-screen sounds and background noise that may hinder the model from learning the desired audio-textual correspondence. To address this problem, we further propose an approach called noise invariant training for training a query-based sound separation model on noisy data. Experimental results show that the proposed models successfully learn text-queried universal sound separation using only noisy unlabeled videos, even achieving competitive performance against a supervised model in some settings.

In this work, we build a simple but strong baseline for sounding video generation. Given base diffusion models for audio and video, we integrate them with additional modules into a single model and train it to make the model jointly generate audio and video. To enhance alignment between audio-video pairs, we introduce two novel mechanisms in our model. The first one is timestep adjustment, which provides different timestep information to each base model. It is designed to align how samples are generated along with timesteps across modalities. The second one is a new design of the additional modules, termed Cross-Modal Conditioning as Positional Encoding (CMC-PE). In CMC-PE, cross-modal information is embedded as if it represents temporal position information, and the embeddings are fed into the model like positional encoding. Compared with the popular cross-attention mechanism, CMC-PE provides a better inductive bias for temporal alignment in the generated data. Experimental results validate the effectiveness of the two newly introduced mechanisms and also demonstrate that our method outperforms existing methods.

We present a neural network architecture designed to naturally learn a positional embedding and overcome the spectral bias towards lower frequencies faced by conventional implicit neural representation networks. Our proposed architecture, SPDER, is a simple MLP that uses an activation function composed of a sinusoidal multiplied by a sublinear function, called the damping function. The sinusoidal enables the network to automatically learn the positional embedding of an input coordinate while the damping passes on the actual coordinate value by preventing it from being projected down to within a finite range of values. Our results indicate that SPDERs speed up training by 10x and converge to losses 1,500-50,000x lower than that of the state-of-the-art for image representation. SPDER is also state-of-the-art in audio representation. The superior representation capability allows SPDER to also excel on multiple downstream tasks such as image super-resolution and video frame interpolation. We provide intuition as to why SPDER significantly improves fitting compared to that of other INR methods while requiring no hyperparameter tuning or preprocessing.

The advancement of audio-language (AL) multimodal learning tasks has been significant in recent years. However, researchers face challenges due to the costly and time-consuming collection process of existing audio-language datasets, which are limited in size. To address this data scarcity issue, we introduce WavCaps, the first large-scale weakly-labelled audio captioning dataset, comprising approximately 400k audio clips with paired captions. We sourced audio clips and their raw descriptions from web sources and a sound event detection dataset. However, the online-harvested raw descriptions are highly noisy and unsuitable for direct use in tasks such as automated audio captioning. To overcome this issue, we propose a three-stage processing pipeline for filtering noisy data and generating high-quality captions, where ChatGPT, a large language model, is leveraged to filter and transform raw descriptions automatically. We conduct a comprehensive analysis of the characteristics of WavCaps dataset and evaluate it on multiple downstream audio-language multimodal learning tasks. The systems trained on WavCaps outperform previous state-of-the-art (SOTA) models by a significant margin. Our aspiration is for the WavCaps dataset we have proposed to facilitate research in audio-language multimodal learning and demonstrate the potential of utilizing ChatGPT to enhance academic research. Our dataset and codes are available at https://github.com/XinhaoMei/WavCaps.

Text-to-audio (TTA) system has recently gained attention for its ability to synthesize general audio based on text descriptions. However, previous studies in TTA have limited generation quality with high computational costs. In this study, we propose AudioLDM, a TTA system that is built on a latent space to learn the continuous audio representations from contrastive language-audio pretraining (CLAP) latents. The pretrained CLAP models enable us to train LDMs with audio embedding while providing text embedding as a condition during sampling. By learning the latent representations of audio signals and their compositions without modeling the cross-modal relationship, AudioLDM is advantageous in both generation quality and computational efficiency. Trained on AudioCaps with a single GPU, AudioLDM achieves state-of-the-art TTA performance measured by both objective and subjective metrics (e.g., frechet distance). Moreover, AudioLDM is the first TTA system that enables various text-guided audio manipulations (e.g., style transfer) in a zero-shot fashion. Our implementation and demos are available at https://audioldm.github.io.

We introduce PixelPlayer, a system that, by leveraging large amounts of unlabeled videos, learns to locate image regions which produce sounds and separate the input sounds into a set of components that represents the sound from each pixel. Our approach capitalizes on the natural synchronization of the visual and audio modalities to learn models that jointly parse sounds and images, without requiring additional manual supervision. Experimental results on a newly collected MUSIC dataset show that our proposed Mix-and-Separate framework outperforms several baselines on source separation. Qualitative results suggest our model learns to ground sounds in vision, enabling applications such as independently adjusting the volume of sound sources.

Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains challenging. This process demands acoustic, semantic, and contextual information for precise speech representations. Existing speech representations generally fall into two categories: acoustic tokens from audio codecs and semantic tokens from speech self-supervised learning models. Although recent efforts have unified acoustic and semantic tokens for improved performance, they overlook the crucial role of contextual representation in comprehensive speech modeling. Our empirical investigations reveal that the absence of contextual representations results in elevated Word Error Rate (WER) and Word Information Lost (WIL) scores in speech transcriptions. To address these limitations, we propose two novel distillation approaches: (1) a language model (LM)-guided distillation method that incorporates contextual information, and (2) a combined LM and self-supervised speech model (SM)-guided distillation technique that effectively distills multimodal representations (acoustic, semantic, and contextual) into a comprehensive speech tokenizer, termed DM-Codec. The DM-Codec architecture adopts a streamlined encoder-decoder framework with a Residual Vector Quantizer (RVQ) and incorporates the LM and SM during the training process. Experiments show DM-Codec significantly outperforms state-of-the-art speech tokenization models, reducing WER by up to 13.46%, WIL by 9.82%, and improving speech quality by 5.84% and intelligibility by 1.85% on the LibriSpeech benchmark dataset. The code, samples, and model checkpoints are available at https://github.com/mubtasimahasan/DM-Codec.

Stochastic latent variable models (LVMs) achieve state-of-the-art performance on natural image generation but are still inferior to deterministic models on speech. In this paper, we develop a speech benchmark of popular temporal LVMs and compare them against state-of-the-art deterministic models. We report the likelihood, which is a much used metric in the image domain, but rarely, or incomparably, reported for speech models. To assess the quality of the learned representations, we also compare their usefulness for phoneme recognition. Finally, we adapt the Clockwork VAE, a state-of-the-art temporal LVM for video generation, to the speech domain. Despite being autoregressive only in latent space, we find that the Clockwork VAE can outperform previous LVMs and reduce the gap to deterministic models by using a hierarchy of latent variables.

While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs. In this paper, we introduce Generative Pre-trained Speech Transformer (GPST), a hierarchical transformer designed for efficient speech language modeling. GPST quantizes audio waveforms into two distinct types of discrete speech representations and integrates them within a hierarchical transformer architecture, allowing for a unified one-stage generation process and enhancing Hi-Res audio generation capabilities. By training on large corpora of speeches in an end-to-end unsupervised manner, GPST can generate syntactically consistent speech with diverse speaker identities. Given a brief 3-second prompt, GPST can produce natural and coherent personalized speech, demonstrating in-context learning abilities. Moreover, our approach can be easily extended to spoken cross-lingual speech generation by incorporating multi-lingual semantic tokens and universal acoustic tokens. Experimental results indicate that GPST significantly outperforms the existing speech language models in terms of word error rate, speech quality, and speaker similarity. See https://youngsheen.github.io/GPST/demo for demo samples.

We demonstrate that language models pre-trained on codified (discretely-encoded) music audio learn representations that are useful for downstream MIR tasks. Specifically, we explore representations from Jukebox (Dhariwal et al. 2020): a music generation system containing a language model trained on codified audio from 1M songs. To determine if Jukebox's representations contain useful information for MIR, we use them as input features to train shallow models on several MIR tasks. Relative to representations from conventional MIR models which are pre-trained on tagging, we find that using representations from Jukebox as input features yields 30% stronger performance on average across four MIR tasks: tagging, genre classification, emotion recognition, and key detection. For key detection, we observe that representations from Jukebox are considerably stronger than those from models pre-trained on tagging, suggesting that pre-training via codified audio language modeling may address blind spots in conventional approaches. We interpret the strength of Jukebox's representations as evidence that modeling audio instead of tags provides richer representations for MIR.

Our goal is to collect a large-scale audio-visual dataset with low label noise from videos in the wild using computer vision techniques. The resulting dataset can be used for training and evaluating audio recognition models. We make three contributions. First, we propose a scalable pipeline based on computer vision techniques to create an audio dataset from open-source media. Our pipeline involves obtaining videos from YouTube; using image classification algorithms to localize audio-visual correspondence; and filtering out ambient noise using audio verification. Second, we use this pipeline to curate the VGGSound dataset consisting of more than 210k videos for 310 audio classes. Third, we investigate various Convolutional Neural Network~(CNN) architectures and aggregation approaches to establish audio recognition baselines for our new dataset. Compared to existing audio datasets, VGGSound ensures audio-visual correspondence and is collected under unconstrained conditions. Code and the dataset are available at http://www.robots.ox.ac.uk/~vgg/data/vggsound/

Traditional neural word embeddings are usually dependent on a richer diversity of vocabulary. However, the language models recline to cover major vocabularies via the word embedding parameters, in particular, for multilingual language models that generally cover a significant part of their overall learning parameters. In this work, we present a new compact embedding structure to reduce the memory footprint of the pre-trained language models with a sacrifice of up to 4% absolute accuracy. The embeddings vectors reconstruction follows a set of subspace embeddings and an assignment procedure via the contextual relationship among tokens from pre-trained language models. The subspace embedding structure calibrates to masked language models, to evaluate our compact embedding structure on similarity and textual entailment tasks, sentence and paraphrase tasks. Our experimental evaluation shows that the subspace embeddings achieve compression rates beyond 99.8% in comparison with the original embeddings for the language models on XNLI and GLUE benchmark suites.

We present a direct speech-to-speech translation (S2ST) model that translates speech from one language to speech in another language without relying on intermediate text generation. We tackle the problem by first applying a self-supervised discrete speech encoder on the target speech and then training a sequence-to-sequence speech-to-unit translation (S2UT) model to predict the discrete representations of the target speech. When target text transcripts are available, we design a joint speech and text training framework that enables the model to generate dual modality output (speech and text) simultaneously in the same inference pass. Experiments on the Fisher Spanish-English dataset show that the proposed framework yields improvement of 6.7 BLEU compared with a baseline direct S2ST model that predicts spectrogram features. When trained without any text transcripts, our model performance is comparable to models that predict spectrograms and are trained with text supervision, showing the potential of our system for translation between unwritten languages. Audio samples are available at https://facebookresearch.github.io/speech_translation/direct_s2st_units/index.html .

Augmenting large language models (LLMs) to understand audio -- including non-speech sounds and non-verbal speech -- is critically important for diverse real-world applications of LLMs. In this paper, we propose Audio Flamingo, a novel audio language model with 1) strong audio understanding abilities, 2) the ability to quickly adapt to unseen tasks via in-context learning and retrieval, and 3) strong multi-turn dialogue abilities. We introduce a series of training techniques, architecture design, and data strategies to enhance our model with these abilities. Extensive evaluations across various audio understanding tasks confirm the efficacy of our method, setting new state-of-the-art benchmarks.

Visual and auditory perception are two crucial ways humans experience the world. Text-to-video generation has made remarkable progress over the past year, but the absence of harmonious audio in generated video limits its broader applications. In this paper, we propose Semantic and Temporal Aligned Video-to-Audio (STA-V2A), an approach that enhances audio generation from videos by extracting both local temporal and global semantic video features and combining these refined video features with text as cross-modal guidance. To address the issue of information redundancy in videos, we propose an onset prediction pretext task for local temporal feature extraction and an attentive pooling module for global semantic feature extraction. To supplement the insufficient semantic information in videos, we propose a Latent Diffusion Model with Text-to-Audio priors initialization and cross-modal guidance. We also introduce Audio-Audio Align, a new metric to assess audio-temporal alignment. Subjective and objective metrics demonstrate that our method surpasses existing Video-to-Audio models in generating audio with better quality, semantic consistency, and temporal alignment. The ablation experiment validated the effectiveness of each module. Audio samples are available at https://y-ren16.github.io/STAV2A.

Cross-modal retrieval methods build a common representation space for samples from multiple modalities, typically from the vision and the language domains. For images and their captions, the multiplicity of the correspondences makes the task particularly challenging. Given an image (respectively a caption), there are multiple captions (respectively images) that equally make sense. In this paper, we argue that deterministic functions are not sufficiently powerful to capture such one-to-many correspondences. Instead, we propose to use Probabilistic Cross-Modal Embedding (PCME), where samples from the different modalities are represented as probabilistic distributions in the common embedding space. Since common benchmarks such as COCO suffer from non-exhaustive annotations for cross-modal matches, we propose to additionally evaluate retrieval on the CUB dataset, a smaller yet clean database where all possible image-caption pairs are annotated. We extensively ablate PCME and demonstrate that it not only improves the retrieval performance over its deterministic counterpart but also provides uncertainty estimates that render the embeddings more interpretable. Code is available at https://github.com/naver-ai/pcme

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets. After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text modality based on the output of the decoder. Leveraging large-scale unlabeled speech and text data, we pre-train SpeechT5 to learn a unified-modal representation, hoping to improve the modeling capability for both speech and text. To align the textual and speech information into this unified semantic space, we propose a cross-modal vector quantization approach that randomly mixes up speech/text states with latent units as the interface between encoder and decoder. Extensive evaluations show the superiority of the proposed SpeechT5 framework on a wide variety of spoken language processing tasks, including automatic speech recognition, speech synthesis, speech translation, voice conversion, speech enhancement, and speaker identification. We release our code and model at https://github.com/microsoft/SpeechT5.

Contrastive language-audio pretraining~(CLAP) has been developed to align the representations of audio and language, achieving remarkable performance in retrieval and classification tasks. However, current CLAP struggles to capture temporal information within audio and text features, presenting substantial limitations for tasks such as audio retrieval and generation. To address this gap, we introduce T-CLAP, a temporal-enhanced CLAP model. We use Large Language Models~(LLMs) and mixed-up strategies to generate temporal-contrastive captions for audio clips from extensive audio-text datasets. Subsequently, a new temporal-focused contrastive loss is designed to fine-tune the CLAP model by incorporating these synthetic data. We conduct comprehensive experiments and analysis in multiple downstream tasks. T-CLAP shows improved capability in capturing the temporal relationship of sound events and outperforms state-of-the-art models by a significant margin.

We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge surge in generative audio, speech, and music models that utilize discrete audio tokens derived from neural compression algorithms, e.g. ENCODEC. However, one of the major drawbacks of this approach is handling the context length. It blows up for high-fidelity generative architecture if one has to account for all the audio contents at various frequencies for the next token prediction. By combining continuous audio representation like the spectrogram and discrete acoustic tokens, we retain the best of both worlds: Have all the information needed from the audio at a specific time instance in a single token, yet allow LLM to predict the future token to allow for sampling and other benefits discrete space provides. We show how our architecture improves the perplexity and negative log-likelihood scores for the next token prediction compared to a token-based LLM for speech and music.

We introduce QuerYD, a new large-scale dataset for retrieval and event localisation in video. A unique feature of our dataset is the availability of two audio tracks for each video: the original audio, and a high-quality spoken description of the visual content. The dataset is based on YouDescribe, a volunteer project that assists visually-impaired people by attaching voiced narrations to existing YouTube videos. This ever-growing collection of videos contains highly detailed, temporally aligned audio and text annotations. The content descriptions are more relevant than dialogue, and more detailed than previous description attempts, which can be observed to contain many superficial or uninformative descriptions. To demonstrate the utility of the QuerYD dataset, we show that it can be used to train and benchmark strong models for retrieval and event localisation. Data, code and models are made publicly available, and we hope that QuerYD inspires further research on video understanding with written and spoken natural language.

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared representations to address the persistent challenge of limited data availability in spoken language understanding tasks. By employing a pre-trained speech-text model, we find that models fine-tuned on text can be effectively transferred to speech testing data. With as little as 1 hour of labeled speech data, our proposed approach achieves comparable performance on spoken language understanding tasks (specifically, sentiment analysis and named entity recognition) when compared to previous methods using speech-only pre-trained models fine-tuned on 10 times more data. Beyond the proof-of-concept study, we also analyze the latent representations. We find that the bottom layers of speech-text models are largely task-agnostic and align speech and text representations into a shared space, while the top layers are more task-specific.

This study aims to construct an audio-video generative model with minimal computational cost by leveraging pre-trained single-modal generative models for audio and video. To achieve this, we propose a novel method that guides single-modal models to cooperatively generate well-aligned samples across modalities. Specifically, given two pre-trained base diffusion models, we train a lightweight joint guidance module to adjust scores separately estimated by the base models to match the score of joint distribution over audio and video. We show that this guidance can be computed using the gradient of the optimal discriminator, which distinguishes real audio-video pairs from fake ones independently generated by the base models. Based on this analysis, we construct a joint guidance module by training this discriminator. Additionally, we adopt a loss function to stabilize the discriminator's gradient and make it work as a noise estimator, as in standard diffusion models. Empirical evaluations on several benchmark datasets demonstrate that our method improves both single-modal fidelity and multimodal alignment with relatively few parameters. The code is available at: https://github.com/SonyResearch/MMDisCo.

We present a joint audio-visual model for isolating a single speech signal from a mixture of sounds such as other speakers and background noise. Solving this task using only audio as input is extremely challenging and does not provide an association of the separated speech signals with speakers in the video. In this paper, we present a deep network-based model that incorporates both visual and auditory signals to solve this task. The visual features are used to "focus" the audio on desired speakers in a scene and to improve the speech separation quality. To train our joint audio-visual model, we introduce AVSpeech, a new dataset comprised of thousands of hours of video segments from the Web. We demonstrate the applicability of our method to classic speech separation tasks, as well as real-world scenarios involving heated interviews, noisy bars, and screaming children, only requiring the user to specify the face of the person in the video whose speech they want to isolate. Our method shows clear advantage over state-of-the-art audio-only speech separation in cases of mixed speech. In addition, our model, which is speaker-independent (trained once, applicable to any speaker), produces better results than recent audio-visual speech separation methods that are speaker-dependent (require training a separate model for each speaker of interest).

Speech understanding as an element of the more generic video understanding using audio-visual large language models (av-LLMs) is a crucial yet understudied aspect. This paper proposes video-SALMONN, a single end-to-end av-LLM for video processing, which can understand not only visual frame sequences, audio events and music, but speech as well. To obtain fine-grained temporal information required by speech understanding, while keeping efficient for other video elements, this paper proposes a novel multi-resolution causal Q-Former (MRC Q-Former) structure to connect pre-trained audio-visual encoders and the backbone large language model. Moreover, dedicated training approaches including the diversity loss and the unpaired audio-visual mixed training scheme are proposed to avoid frames or modality dominance. On the introduced speech-audio-visual evaluation benchmark, video-SALMONN achieves more than 25\% absolute accuracy improvements on the video-QA task and over 30\% absolute accuracy improvements on audio-visual QA tasks with human speech. In addition, video-SALMONN demonstrates remarkable video comprehension and reasoning abilities on tasks that are unprecedented by other av-LLMs. Our training code and model checkpoints are available at \url{https://github.com/bytedance/SALMONN/}.

We present PAST, a novel end-to-end framework that jointly models phonetic information alongside signal reconstruction, eliminating the need for external pretrained models. Unlike previous approaches that rely on pretrained self-supervised models, PAST employs supervised phonetic data, directly integrating domain knowledge into the tokenization process via auxiliary tasks. Additionally, we introduce a streamable, causal variant of PAST, enabling real-time speech applications. Results demonstrate that PAST surpasses existing evaluated baseline tokenizers across common evaluation metrics, including phonetic representation and speech reconstruction. Notably, PAST also achieves superior performance when serving as a speech representation for speech language models, further highlighting its effectiveness as a foundation for spoken language generation. To foster further research, we release the full implementation. For code, model checkpoints, and samples see: https://pages.cs.huji.ac.il/adiyoss-lab/PAST

We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker identity. This allows to synthesize speech in a controllable manner. We analyze various state-of-the-art, self-supervised representation learning methods and shed light on the advantages of each method while considering reconstruction quality and disentanglement properties. Specifically, we evaluate the F0 reconstruction, speaker identification performance (for both resynthesis and voice conversion), recordings' intelligibility, and overall quality using subjective human evaluation. Lastly, we demonstrate how these representations can be used for an ultra-lightweight speech codec. Using the obtained representations, we can get to a rate of 365 bits per second while providing better speech quality than the baseline methods. Audio samples can be found under the following link: speechbot.github.io/resynthesis.

This report introduces PixelBytes Embedding, a novel approach for unified multimodal representation learning. Our method captures diverse inputs in a single, cohesive representation, enabling emergent properties for multimodal sequence generation, particularly for text and pixelated images. Inspired by state-of-the-art sequence models such as Image Transformers, PixelCNN, and Mamba-Bytes, PixelBytes aims to address the challenges of integrating different data types. We explore various model architectures, including Recurrent Neural Networks (RNNs), State Space Models (SSMs), and Attention-based models, focusing on bidirectional processing and our innovative PxBy embedding technique. Our experiments, conducted on a specialized PixelBytes Pok{\'e}mon dataset, demonstrate that bidirectional sequence models with PxBy embedding and convolutional layers can generate coherent multimodal sequences. This work contributes to the advancement of integrated AI models capable of understanding and generating multimodal data in a unified manner.

Despite Multi-modal Large Language Models (MM-LLMs) have made exciting strides recently, they are still struggling to efficiently model the interactions among multi-modal inputs and the generation in non-textual modalities. In this work, we propose TEAL (Tokenize and Embed ALl)}, an approach to treat the input from any modality as a token sequence and learn a joint embedding space for all modalities. Specifically, for the input from any modality, TEAL first discretizes it into a token sequence with the off-the-shelf tokenizer and embeds the token sequence into a joint embedding space with a learnable embedding matrix. MM-LLMs just need to predict the multi-modal tokens autoregressively as the textual LLMs do. Finally, the corresponding de-tokenizer is applied to generate the output in each modality based on the predicted token sequence. With the joint embedding space, TEAL enables the frozen LLMs to perform both understanding and generation tasks involving non-textual modalities, such as image and audio. Thus, the textual LLM can just work as an interface and maintain its high performance in textual understanding and generation. Experiments show that TEAL achieves substantial improvements in multi-modal understanding, and implements a simple scheme for multi-modal generations.

Large Language Models (LLMs) have ushered in a new wave of artificial intelligence advancements impacting every scientific field and discipline. They are trained on a simple objective: to predict the next token given the previous context. We live in a world where most of the data around us, e.g., text, audio, and music, has a multi-scale structure associated with it. This paper infuses LLMs with traditional signal processing ideas, namely wavelets, during pre-training to take advantage of the structure. Without adding any extra parameters to a GPT-style LLM architecture, we achieve the same pre-training performance almost twice as fast in text, raw audio, and symbolic music. This is achieved by imposing a structure on intermediate embeddings. When trained for the same number of training steps, we achieve significant gains in performance, which is comparable to pre-training a larger neural architecture. Our architecture allows every next token prediction access to intermediate embeddings at different temporal resolutions in every Transformer decoder block. This work will hopefully pave the way for incorporating multi-rate signal processing ideas into traditional LLM pre-training. Further, we showcase pushing model performance by improving internal structure instead of just going after scale.

Text-to-speech (TTS) methods have shown promising results in voice cloning, but they require a large number of labeled text-speech pairs. Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech representations(semantic \& acoustic) and using two sequence-to-sequence tasks to enable training with minimal supervision. However, existing methods suffer from information redundancy and dimension explosion in semantic representation, and high-frequency waveform distortion in discrete acoustic representation. Autoregressive frameworks exhibit typical instability and uncontrollability issues. And non-autoregressive frameworks suffer from prosodic averaging caused by duration prediction models. To address these issues, we propose a minimally-supervised high-fidelity speech synthesis method, where all modules are constructed based on the diffusion models. The non-autoregressive framework enhances controllability, and the duration diffusion model enables diversified prosodic expression. Contrastive Token-Acoustic Pretraining (CTAP) is used as an intermediate semantic representation to solve the problems of information redundancy and dimension explosion in existing semantic coding methods. Mel-spectrogram is used as the acoustic representation. Both semantic and acoustic representations are predicted by continuous variable regression tasks to solve the problem of high-frequency fine-grained waveform distortion. Experimental results show that our proposed method outperforms the baseline method. We provide audio samples on our website.

Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years. Despite some progress, existing methods are mostly limited to highly curated datasets (e.g., K400) and exhibit unsatisfactory out-of-the-box representations. We argue that it is due to the fact that they only capture pixel-level knowledge rather than spatiotemporal semantics, which hinders further progress in video understanding. Inspired by the great success of image-text pre-training (e.g., CLIP), we take the first step to exploit language semantics to boost transferable spatiotemporal representation learning. We introduce a new pretext task, Turning to Video for Transcript Sorting (TVTS), which sorts shuffled ASR scripts by attending to learned video representations. We do not rely on descriptive captions and learn purely from video, i.e., leveraging the natural transcribed speech knowledge to provide noisy but useful semantics over time. Our method enforces the vision model to contextualize what is happening over time so that it can re-organize the narrative transcripts, and can seamlessly apply to large-scale uncurated video data in the real world. Our method demonstrates strong out-of-the-box spatiotemporal representations on diverse benchmarks, e.g., +13.6% gains over VideoMAE on SSV2 via linear probing. The code is available at https://github.com/TencentARC/TVTS.

This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a vocoder to synthesize timedomain waveforms from those spectrograms. Our model achieves a mean opinion score (MOS) of 4.53 comparable to a MOS of 4.58 for professionally recorded speech. To validate our design choices, we present ablation studies of key components of our system and evaluate the impact of using mel spectrograms as the input to WaveNet instead of linguistic, duration, and F_0 features. We further demonstrate that using a compact acoustic intermediate representation enables significant simplification of the WaveNet architecture.

Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the type or extent of information encoded in the pre-trained representations themselves. Developing such insights can help understand the capabilities and limits of these models and enable the research community to more efficiently develop their usage for downstream applications. In this work, we begin to fill this gap by examining one recent and successful pre-trained model (wav2vec 2.0), via its intermediate representation vectors, using a suite of analysis tools. We use the metrics of canonical correlation, mutual information, and performance on simple downstream tasks with non-parametric probes, in order to (i) query for acoustic and linguistic information content, (ii) characterize the evolution of information across model layers, and (iii) understand how fine-tuning the model for automatic speech recognition (ASR) affects these observations. Our findings motivate modifying the fine-tuning protocol for ASR, which produces improved word error rates in a low-resource setting.

Generative Spoken Language Modeling research focuses on optimizing speech Language Models (LMs) using raw audio recordings without accessing any textual supervision. Such speech LMs usually operate over discrete units obtained from quantizing internal representations of self-supervised models. Although such units show impressive modeling results, their robustness capabilities have not been extensively investigated. This work focuses on improving the robustness of discrete input representations for generative spoken language modeling. First, we formally define how to measure the robustness of such representations to various signal variations that do not alter the spoken information (e.g., time-stretch). Next, we empirically demonstrate how current state-of-the-art representation models lack robustness to such variations. To overcome this, we propose an effective and efficient method to learn robust discrete speech representation for generative spoken language modeling. The proposed approach is based on applying a set of signal transformations to the speech signal and optimizing the model using an iterative pseudo-labeling scheme. Our method significantly improves over the evaluated baselines when considering encoding and modeling metrics. We additionally evaluate our method on the speech-to-speech translation task, considering Spanish-English and French-English translations, and show the proposed approach outperforms the evaluated baselines.

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained on a speaker verification task using an independent dataset of noisy speech from thousands of speakers without transcripts, to generate a fixed-dimensional embedding vector from seconds of reference speech from a target speaker; (2) a sequence-to-sequence synthesis network based on Tacotron 2, which generates a mel spectrogram from text, conditioned on the speaker embedding; (3) an auto-regressive WaveNet-based vocoder that converts the mel spectrogram into a sequence of time domain waveform samples. We demonstrate that the proposed model is able to transfer the knowledge of speaker variability learned by the discriminatively-trained speaker encoder to the new task, and is able to synthesize natural speech from speakers that were not seen during training. We quantify the importance of training the speaker encoder on a large and diverse speaker set in order to obtain the best generalization performance. Finally, we show that randomly sampled speaker embeddings can be used to synthesize speech in the voice of novel speakers dissimilar from those used in training, indicating that the model has learned a high quality speaker representation.

Self-supervised models have revolutionized speech processing, achieving new levels of performance in a wide variety of tasks with limited resources. However, the inner workings of these models are still opaque. In this paper, we aim to analyze the encoded contextual representation of these foundation models based on their inter- and intra-model similarity, independent of any external annotation and task-specific constraint. We examine different SSL models varying their training paradigm -- Contrastive (Wav2Vec2.0) and Predictive models (HuBERT); and model sizes (base and large). We explore these models on different levels of localization/distributivity of information including (i) individual neurons; (ii) layer representation; (iii) attention weights and (iv) compare the representations with their finetuned counterparts.Our results highlight that these models converge to similar representation subspaces but not to similar neuron-localized concepts\footnote{A concept represents a coherent fragment of knowledge, such as ``a class containing certain objects as elements, where the objects have certain properties. We made the code publicly available for facilitating further research, we publicly released our code.

Visual speech recognition models extract visual features in a hierarchical manner. At the lower level, there is a visual front-end with a limited temporal receptive field that processes the raw pixels depicting the lips or faces. At the higher level, there is an encoder that attends to the embeddings produced by the front-end over a large temporal receptive field. Previous work has focused on improving the visual front-end of the model to extract more useful features for speech recognition. Surprisingly, our work shows that complex visual front-ends are not necessary. Instead of allocating resources to a sophisticated visual front-end, we find that a linear visual front-end paired with a larger Conformer encoder results in lower latency, more efficient memory usage, and improved WER performance. We achieve a new state-of-the-art of 12.8% WER for visual speech recognition on the TED LRS3 dataset, which rivals the performance of audio-only models from just four years ago.

Propelled by the breakthrough in deep generative models, audio-to-image generation has emerged as a pivotal cross-model task that converts complex auditory signals into rich visual representations. However, previous works only focus on single-source audio inputs for image generation, ignoring the multi-source characteristic in natural auditory scenes, thus limiting the performance in generating comprehensive visual content. To bridge this gap, a method called MACS is proposed to conduct multi-source audio-to-image generation. This is the first work that explicitly separates multi-source audio to capture the rich audio components before image generation. MACS is a two-stage method. In the first stage, multi-source audio inputs are separated by a weakly supervised method, where the audio and text labels are semantically aligned by casting into a common space using the large pre-trained CLAP model. We introduce a ranking loss to consider the contextual significance of the separated audio signals. In the second stage, efficient image generation is achieved by mapping the separated audio signals to the generation condition using only a trainable adapter and a MLP layer. We preprocess the LLP dataset as the first full multi-source audio-to-image generation benchmark. The experiments are conducted on multi-source, mixed-source, and single-source audio-to-image generation tasks. The proposed MACS outperforms the current state-of-the-art methods in 17 of the 21 evaluation indexes on all tasks and delivers superior visual quality. The code will be publicly available.

Massive multi-modality datasets play a significant role in facilitating the success of large video-language models. However, current video-language datasets primarily provide text descriptions for visual frames, considering audio to be weakly related information. They usually overlook exploring the potential of inherent audio-visual correlation, leading to monotonous annotation within each modality instead of comprehensive and precise descriptions. Such ignorance results in the difficulty of multiple cross-modality studies. To fulfill this gap, we present MMTrail, a large-scale multi-modality video-language dataset incorporating more than 20M trailer clips with visual captions, and 2M high-quality clips with multimodal captions. Trailers preview full-length video works and integrate context, visual frames, and background music. In particular, the trailer has two main advantages: (1) the topics are diverse, and the content characters are of various types, e.g., film, news, and gaming. (2) the corresponding background music is custom-designed, making it more coherent with the visual context. Upon these insights, we propose a systemic captioning framework, achieving various modality annotations with more than 27.1k hours of trailer videos. Here, to ensure the caption retains music perspective while preserving the authority of visual context, we leverage the advanced LLM to merge all annotations adaptively. In this fashion, our MMtrail dataset potentially paves the path for fine-grained large multimodal-language model training. In experiments, we provide evaluation metrics and benchmark results on our dataset, demonstrating the high quality of our annotation and its effectiveness for model training.

We address the task of video chaptering, i.e., partitioning a long video timeline into semantic units and generating corresponding chapter titles. While relatively underexplored, automatic chaptering has the potential to enable efficient navigation and content retrieval in long-form videos. In this paper, we achieve strong chaptering performance on hour-long videos by efficiently addressing the problem in the text domain with our 'Chapter-Llama' framework. Specifically, we leverage a pretrained large language model (LLM) with large context window, and feed as input (i) speech transcripts and (ii) captions describing video frames, along with their respective timestamps. Given the inefficiency of exhaustively captioning all frames, we propose a lightweight speech-guided frame selection strategy based on speech transcript content, and experimentally demonstrate remarkable advantages. We train the LLM to output timestamps for the chapter boundaries, as well as free-form chapter titles. This simple yet powerful approach scales to processing one-hour long videos in a single forward pass. Our results demonstrate substantial improvements (e.g., 45.3 vs 26.7 F1 score) over the state of the art on the recent VidChapters-7M benchmark. To promote further research, we release our code and models at our project page.

With the rapid progress of speech language models (SLMs), discrete speech tokens have emerged as a core interface between speech and text, enabling unified modeling across modalities. Recent speech tokenization approaches aim to isolate semantic information from low-level acoustics to better align with language models. In particular, previous methods use SSL teachers such as HuBERT to extract semantic representations, which are then distilled into a semantic quantizer to suppress acoustic redundancy as well as capture content-related latent structures. However, they still produce speech token sequences significantly longer than their textual counterparts, creating challenges for efficient speech-language modeling. Reducing the frame rate is a natural solution, but standard techniques, such as rigid average pooling across frames, can distort or dilute the semantic structure required for effective LM alignment. To address this, we propose LM-SPT, a speech tokenization method that introduces a novel semantic distillation. Instead of directly matching teacher and student features via pooling, we reconstruct speech solely from semantic tokens and minimize the discrepancy between the encoded representations of the original and reconstructed waveforms, obtained from a frozen automatic speech recognition (ASR) encoder. This indirect yet data-driven supervision enables the tokenizer to learn discrete units that are more semantically aligned with language models. LM-SPT further incorporates architectural improvements to the encoder and decoder for speech tokenization, and supports multiple frame rates, including 25Hz, 12.5Hz, and 6.25Hz. Experimental results show that LM-SPT achieves superior reconstruction fidelity compared to baselines, and that SLMs trained with LM-SPT tokens achieve competitive performances on speech-to-text and consistently outperform baselines on text-to-speech tasks.

The rapid advancements in large language models (LLMs) have significantly enhanced natural language processing capabilities, facilitating the development of AudioLLMs that process and understand speech and audio inputs alongside text. Existing AudioLLMs typically combine a pre-trained audio encoder with a pre-trained LLM, which are subsequently finetuned on specific audio tasks. However, the pre-trained audio encoder has constrained capacity to capture features for new tasks and datasets. To address this, we propose to incorporate mixtures of `weak' encoders (MoWE) into the AudioLLM framework. MoWE supplements a base encoder with a pool of relatively light weight encoders, selectively activated based on the audio input to enhance feature extraction without significantly increasing model size. Our empirical results demonstrate that MoWE effectively improves multi-task performance, broadening the applicability of AudioLLMs to more diverse audio tasks.

Language models have been successfully used to model natural signals, such as images, speech, and music. A key component of these models is a high quality neural compression model that can compress high-dimensional natural signals into lower dimensional discrete tokens. To that end, we introduce a high-fidelity universal neural audio compression algorithm that achieves ~90x compression of 44.1 KHz audio into tokens at just 8kbps bandwidth. We achieve this by combining advances in high-fidelity audio generation with better vector quantization techniques from the image domain, along with improved adversarial and reconstruction losses. We compress all domains (speech, environment, music, etc.) with a single universal model, making it widely applicable to generative modeling of all audio. We compare with competing audio compression algorithms, and find our method outperforms them significantly. We provide thorough ablations for every design choice, as well as open-source code and trained model weights. We hope our work can lay the foundation for the next generation of high-fidelity audio modeling.

Large language models have revolutionized natural language processing by leveraging self-supervised pretraining on vast textual data. Inspired by this success, researchers have investigated complicated speech tokenization methods to discretize continuous speech signals so that language modeling techniques can be applied to speech data. However, existing approaches either model semantic tokens, potentially losing acoustic information, or model acoustic tokens, risking the loss of semantic information. Having multiple token types also complicates the architecture and requires additional pretraining. Here we show that discretizing mel-filterbank channels into discrete intensity bins produces a simple representation (dMel), that performs better than other existing speech tokenization methods. Using a transformer decoder-only architecture for speech-text modeling, we comprehensively evaluate different speech tokenization methods on speech recognition (ASR), speech synthesis (TTS). Our results demonstrate the effectiveness of dMel in achieving high performance on both tasks within a unified framework, paving the way for efficient and effective joint modeling of speech and text.

Recent advancements in Deep and Self-Supervised Learning (SSL) have led to substantial improvements in Speech Emotion Recognition (SER) performance, reaching unprecedented levels. However, obtaining sufficient amounts of accurately labeled data for training or fine-tuning the models remains a costly and challenging task. In this paper, we propose a multi-view SSL pre-training technique that can be applied to various representations of speech, including the ones generated by large speech models, to improve SER performance in scenarios where annotations are limited. Our experiments, based on wav2vec 2.0, spectral and paralinguistic features, demonstrate that the proposed framework boosts the SER performance, by up to 10% in Unweighted Average Recall, in settings with extremely sparse data annotations.

The objective of this paper is an automatic Audio Description (AD) model that ingests movies and outputs AD in text form. Generating high-quality movie AD is challenging due to the dependency of the descriptions on context, and the limited amount of training data available. In this work, we leverage the power of pretrained foundation models, such as GPT and CLIP, and only train a mapping network that bridges the two models for visually-conditioned text generation. In order to obtain high-quality AD, we make the following four contributions: (i) we incorporate context from the movie clip, AD from previous clips, as well as the subtitles; (ii) we address the lack of training data by pretraining on large-scale datasets, where visual or contextual information is unavailable, e.g. text-only AD without movies or visual captioning datasets without context; (iii) we improve on the currently available AD datasets, by removing label noise in the MAD dataset, and adding character naming information; and (iv) we obtain strong results on the movie AD task compared with previous methods.

Linking sheet music images to audio recordings remains a key problem for the development of efficient cross-modal music retrieval systems. One of the fundamental approaches toward this task is to learn a cross-modal embedding space via deep neural networks that is able to connect short snippets of audio and sheet music. However, the scarcity of annotated data from real musical content affects the capability of such methods to generalize to real retrieval scenarios. In this work, we investigate whether we can mitigate this limitation with self-supervised contrastive learning, by exposing a network to a large amount of real music data as a pre-training step, by contrasting randomly augmented views of snippets of both modalities, namely audio and sheet images. Through a number of experiments on synthetic and real piano data, we show that pre-trained models are able to retrieve snippets with better precision in all scenarios and pre-training configurations. Encouraged by these results, we employ the snippet embeddings in the higher-level task of cross-modal piece identification and conduct more experiments on several retrieval configurations. In this task, we observe that the retrieval quality improves from 30% up to 100% when real music data is present. We then conclude by arguing for the potential of self-supervised contrastive learning for alleviating the annotated data scarcity in multi-modal music retrieval models.

We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities, including speech, text, images, and music. AnyGPT can be trained stably without any alterations to the current large language model (LLM) architecture or training paradigms. Instead, it relies exclusively on data-level preprocessing, facilitating the seamless integration of new modalities into LLMs, akin to the incorporation of new languages. We build a multimodal text-centric dataset for multimodal alignment pre-training. Utilizing generative models, we synthesize the first large-scale any-to-any multimodal instruction dataset. It consists of 108k samples of multi-turn conversations that intricately interweave various modalities, thus equipping the model to handle arbitrary combinations of multimodal inputs and outputs. Experimental results demonstrate that AnyGPT is capable of facilitating any-to-any multimodal conversation while achieving performance comparable to specialized models across all modalities, proving that discrete representations can effectively and conveniently unify multiple modalities within a language model. Demos are shown in https://junzhan2000.github.io/AnyGPT.github.io/

Most of existing audio fingerprinting systems have limitations to be used for high-specific audio retrieval at scale. In this work, we generate a low-dimensional representation from a short unit segment of audio, and couple this fingerprint with a fast maximum inner-product search. To this end, we present a contrastive learning framework that derives from the segment-level search objective. Each update in training uses a batch consisting of a set of pseudo labels, randomly selected original samples, and their augmented replicas. These replicas can simulate the degrading effects on original audio signals by applying small time offsets and various types of distortions, such as background noise and room/microphone impulse responses. In the segment-level search task, where the conventional audio fingerprinting systems used to fail, our system using 10x smaller storage has shown promising results. Our code and dataset are available at https://mimbres.github.io/neural-audio-fp/.

Training deep learning models for video classification from audio-visual data commonly requires immense amounts of labeled training data collected via a costly process. A challenging and underexplored, yet much cheaper, setup is few-shot learning from video data. In particular, the inherently multi-modal nature of video data with sound and visual information has not been leveraged extensively for the few-shot video classification task. Therefore, we introduce a unified audio-visual few-shot video classification benchmark on three datasets, i.e. the VGGSound-FSL, UCF-FSL, ActivityNet-FSL datasets, where we adapt and compare ten methods. In addition, we propose AV-DIFF, a text-to-feature diffusion framework, which first fuses the temporal and audio-visual features via cross-modal attention and then generates multi-modal features for the novel classes. We show that AV-DIFF obtains state-of-the-art performance on our proposed benchmark for audio-visual (generalised) few-shot learning. Our benchmark paves the way for effective audio-visual classification when only limited labeled data is available. Code and data are available at https://github.com/ExplainableML/AVDIFF-GFSL.

Contrastive language-audio pre-training (CLAP) enables zero-shot (ZS) inference of audio and exhibits promising performance in several classification tasks. However, conventional audio representations are still crucial for many tasks where ZS is not applicable (e.g., regression problems). Here, we explore a new representation, a general-purpose audio-language representation, that performs well in both ZS and transfer learning. To do so, we propose a new method, M2D-CLAP, which combines self-supervised learning Masked Modeling Duo (M2D) and CLAP. M2D learns an effective representation to model audio signals, and CLAP aligns the representation with text embedding. As a result, M2D-CLAP learns a versatile representation that allows for both ZS and transfer learning. Experiments show that M2D-CLAP performs well on linear evaluation, fine-tuning, and ZS classification with a GTZAN state-of-the-art of 75.17%, thus achieving a general-purpose audio-language representation.

The rapid development of large-scale text-to-speech (TTS) models has led to significant advancements in modeling diverse speaker prosody and voices. However, these models often face issues such as slow inference speeds, reliance on complex pre-trained neural codec representations, and difficulties in achieving naturalness and high similarity to reference speakers. To address these challenges, this work introduces StyleTTS-ZS, an efficient zero-shot TTS model that leverages distilled time-varying style diffusion to capture diverse speaker identities and prosodies. We propose a novel approach that represents human speech using input text and fixed-length time-varying discrete style codes to capture diverse prosodic variations, trained adversarially with multi-modal discriminators. A diffusion model is then built to sample this time-varying style code for efficient latent diffusion. Using classifier-free guidance, StyleTTS-ZS achieves high similarity to the reference speaker in the style diffusion process. Furthermore, to expedite sampling, the style diffusion model is distilled with perceptual loss using only 10k samples, maintaining speech quality and similarity while reducing inference speed by 90%. Our model surpasses previous state-of-the-art large-scale zero-shot TTS models in both naturalness and similarity, offering a 10-20 faster sampling speed, making it an attractive alternative for efficient large-scale zero-shot TTS systems. The audio demo, code and models are available at https://styletts-zs.github.io/.

Audio-language models have shown promising results in various sound understanding tasks, yet they remain limited in their ability to reason over the fine-grained semantics of sound. In this paper, we present AudSemThinker, a model whose reasoning is structured around a framework of auditory semantics inspired by human cognition. To support this, we introduce AudSem, a novel dataset specifically curated for semantic descriptor reasoning in audio-language models. AudSem addresses the persistent challenge of data contamination in zero-shot evaluations by providing a carefully filtered collection of audio samples paired with captions generated through a robust multi-stage pipeline. Our experiments demonstrate that AudSemThinker outperforms state-of-the-art models across multiple training settings, highlighting its strength in semantic audio reasoning. Both AudSemThinker and the AudSem dataset are released publicly.

Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in higher-level spoken language understanding tasks, including using end-to-end models, but there are fewer annotated datasets for such tasks. At the same time, recent work shows the possibility of pre-training generic representations and then fine-tuning for several tasks using relatively little labeled data. We propose to create a suite of benchmark tasks for Spoken Language Understanding Evaluation (SLUE) consisting of limited-size labeled training sets and corresponding evaluation sets. This resource would allow the research community to track progress, evaluate pre-trained representations for higher-level tasks, and study open questions such as the utility of pipeline versus end-to-end approaches. We present the first phase of the SLUE benchmark suite, consisting of named entity recognition, sentiment analysis, and ASR on the corresponding datasets. We focus on naturally produced (not read or synthesized) speech, and freely available datasets. We provide new transcriptions and annotations on subsets of the VoxCeleb and VoxPopuli datasets, evaluation metrics and results for baseline models, and an open-source toolkit to reproduce the baselines and evaluate new models.

Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this paper, we introduce a novel semi-supervised text-to-speech synthesis model that learns from both paired and unpaired data to address this challenge. The key component of the proposed model is a dynamic quantized representation module, which is integrated into a sequential autoencoder. When given paired data, the module incorporates a trainable codebook that learns quantized representations under the supervision of the paired data. However, due to the limited paired data in low-resource scenario, these paired data are difficult to cover all phonemes. Then unpaired data is fed to expand the dynamic codebook by adding quantized representation vectors that are sufficiently distant from the existing ones during training. Experiments show that with less than 120 minutes of paired data, the proposed method outperforms existing methods in both subjective and objective metrics.

Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics while enabling efficient storage and inference, as well as competitive performance across diverse downstream tasks.They provide a practical alternative to continuous features, enabling the integration of speech and audio into modern large language models (LLMs). As interest in token-based audio processing grows, various tokenization methods have emerged, and several surveys have reviewed the latest progress in the field. However, existing studies often focus on specific domains or tasks and lack a unified comparison across various benchmarks. This paper presents a systematic review and benchmark of discrete audio tokenizers, covering three domains: speech, music, and general audio. We propose a taxonomy of tokenization approaches based on encoder-decoder, quantization techniques, training paradigm, streamability, and application domains. We evaluate tokenizers on multiple benchmarks for reconstruction, downstream performance, and acoustic language modeling, and analyze trade-offs through controlled ablation studies. Our findings highlight key limitations, practical considerations, and open challenges, providing insight and guidance for future research in this rapidly evolving area. For more information, including our main results and tokenizer database, please refer to our website: https://poonehmousavi.github.io/dates-website/.

Existing emotional speech synthesis methods often utilize an utterance-level style embedding extracted from reference audio, neglecting the inherent multi-scale property of speech prosody. We introduce ED-TTS, a multi-scale emotional speech synthesis model that leverages Speech Emotion Diarization (SED) and Speech Emotion Recognition (SER) to model emotions at different levels. Specifically, our proposed approach integrates the utterance-level emotion embedding extracted by SER with fine-grained frame-level emotion embedding obtained from SED. These embeddings are used to condition the reverse process of the denoising diffusion probabilistic model (DDPM). Additionally, we employ cross-domain SED to accurately predict soft labels, addressing the challenge of a scarcity of fine-grained emotion-annotated datasets for supervising emotional TTS training.

This work introduces Text2FX, a method that leverages CLAP embeddings and differentiable digital signal processing to control audio effects, such as equalization and reverberation, using open-vocabulary natural language prompts (e.g., "make this sound in-your-face and bold"). Text2FX operates without retraining any models, relying instead on single-instance optimization within the existing embedding space, thus enabling a flexible, scalable approach to open-vocabulary sound transformations through interpretable and disentangled FX manipulation. We show that CLAP encodes valuable information for controlling audio effects and propose two optimization approaches using CLAP to map text to audio effect parameters. While we demonstrate with CLAP, this approach is applicable to any shared text-audio embedding space. Similarly, while we demonstrate with equalization and reverberation, any differentiable audio effect may be controlled. We conduct a listener study with diverse text prompts and source audio to evaluate the quality and alignment of these methods with human perception. Demos and code are available at anniejchu.github.io/text2fx.

Recently, video-language understanding has achieved great success through large-scale pre-training. However, data scarcity remains a prevailing challenge. This study quantitatively reveals an "impossible trinity" among data quantity, diversity, and quality in pre-training datasets. Recent efforts seek to refine large-scale, diverse ASR datasets compromised by low quality through synthetic annotations. These methods successfully leverage useful information in multimodal video content (frames, tags, ASR transcripts, etc.) to refine the original annotations. Nevertheless, they struggle to mitigate noise within synthetic annotations and lack scalability as the dataset size expands. To address these issues, we introduce the Video DataFlywheel framework, which iteratively refines video annotations with improved noise control methods. For iterative refinement, we first leverage a video-language model to generate synthetic annotations, resulting in a refined dataset. Then, we pre-train on it and fine-tune on human refinement examples for a stronger model. These processes are repeated for continuous improvement. For noise control, we present AdaTaiLr, a novel noise control method that requires weaker assumptions on noise distribution, thereby proving more effective in large datasets with theoretical guarantees. The combination of iterative refinement and AdaTaiLr can achieve better scalability in video-language understanding. Extensive experiments show that our framework outperforms existing data refinement baselines, delivering a 3% performance boost and improving dataset quality with minimal diversity loss. Furthermore, our refined dataset facilitates significant improvements in various video-language understanding tasks, including video question answering and text-video retrieval.

Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary model APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) transcripts. Specifically, we propose a novel streaming training approach that densely interleaves the ASR words and video frames according to their timestamps. Compared to previous studies in vision-language representation with ASR, our method naturally fits the streaming characteristics of ASR, thus enabling the model to learn temporally-aligned, fine-grained vision-language modeling. To support the training algorithm, we introduce a data production pipeline to process YouTube videos and their closed captions (CC, same as ASR), resulting in Live-CC-5M dataset for pre-training and Live-WhisperX-526K dataset for high-quality supervised fine-tuning (SFT). Remarkably, even without SFT, the ASR-only pre-trained LiveCC-7B-Base model demonstrates competitive general video QA performance and exhibits a new capability in real-time video commentary. To evaluate this, we carefully design a new LiveSports-3K benchmark, using LLM-as-a-judge to measure the free-form commentary. Experiments show our final LiveCC-7B-Instruct model can surpass advanced 72B models (Qwen2.5-VL-72B-Instruct, LLaVA-Video-72B) in commentary quality even working in a real-time mode. Meanwhile, it achieves state-of-the-art results at the 7B/8B scale on popular video QA benchmarks such as VideoMME and OVOBench, demonstrating the broad generalizability of our approach. All resources of this paper have been released at https://showlab.github.io/livecc.

In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose adopting representation learning, where an encoder is trained using unlabeled data. This learning framework enables the study and implementation of a practically relevant use case where only a small amount of the labels is available in a continual learning context. We also make the empirical observation that a similarity-based representation learning method within this framework is robust to forgetting even if no explicit mechanism against forgetting is employed. We show that this approach obtains similar performance compared to several distillation-based continual learning methods when employed on self-supervised representation learning methods.

To scale neural speech synthesis to various real-world languages, we present a multilingual end-to-end framework that maps byte inputs to spectrograms, thus allowing arbitrary input scripts. Besides strong results on 40+ languages, the framework demonstrates capabilities to adapt to new languages under extreme low-resource and even few-shot scenarios of merely 40s transcribed recording, without the need of per-language resources like lexicon, extra corpus, auxiliary models, or linguistic expertise, thus ensuring scalability. While it retains satisfactory intelligibility and naturalness matching rich-resource models. Exhaustive comparative and ablation studies are performed to reveal the potential of the framework for low-resource languages. Furthermore, we propose a novel method to extract language-specific sub-networks in a multilingual model for a better understanding of its mechanism.

Video recordings of speech contain correlated audio and visual information, providing a strong signal for speech representation learning from the speaker's lip movements and the produced sound. We introduce Audio-Visual Hidden Unit BERT (AV-HuBERT), a self-supervised representation learning framework for audio-visual speech, which masks multi-stream video input and predicts automatically discovered and iteratively refined multimodal hidden units. AV-HuBERT learns powerful audio-visual speech representation benefiting both lip-reading and automatic speech recognition. On the largest public lip-reading benchmark LRS3 (433 hours), AV-HuBERT achieves 32.5% WER with only 30 hours of labeled data, outperforming the former state-of-the-art approach (33.6%) trained with a thousand times more transcribed video data (31K hours). The lip-reading WER is further reduced to 26.9% when using all 433 hours of labeled data from LRS3 and combined with self-training. Using our audio-visual representation on the same benchmark for audio-only speech recognition leads to a 40% relative WER reduction over the state-of-the-art performance (1.3% vs 2.3%). Our code and models are available at https://github.com/facebookresearch/av_hubert

We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for cross modality learning. A self-supervised speech subtask leverages unlabelled speech data, and a (self-)supervised text to text subtask makes use of abundant text training data. Two auxiliary supervised speech tasks are included to unify speech and text modeling space. Our contribution lies in integrating linguistic information from the text corpus into the speech pre-training. Detailed analysis reveals learning interference among subtasks. Two pre-training configurations for speech translation and recognition, respectively, are presented to alleviate subtask interference. Our experiments show the proposed method can effectively fuse speech and text information into one model. It achieves between 1.7 and 2.3 BLEU improvement above the state of the art on the MuST-C speech translation dataset and comparable WERs to wav2vec 2.0 on the Librispeech speech recognition task.

In this study, we introduce YODAS (YouTube-Oriented Dataset for Audio and Speech), a large-scale, multilingual dataset comprising currently over 500k hours of speech data in more than 100 languages, sourced from both labeled and unlabeled YouTube speech datasets. The labeled subsets, including manual or automatic subtitles, facilitate supervised model training. Conversely, the unlabeled subsets are apt for self-supervised learning applications. YODAS is distinctive as the first publicly available dataset of its scale, and it is distributed under a Creative Commons license. We introduce the collection methodology utilized for YODAS, which contributes to the large-scale speech dataset construction. Subsequently, we provide a comprehensive analysis of speech, text contained within the dataset. Finally, we describe the speech recognition baselines over the top-15 languages.

What happens when we push audio-visual alignment to its absolute limits? To systematically investigate this question, we needed datasets with granular alignment quality annotations, but existing datasets treat alignment as binary, either synchronized or not. To address this limitation, we developed a comprehensive dataset featuring detailed alignment scores that reveal the hidden spectrum of audio-visual perceptual correspondence. Using these precise scores, we create "superaligned" representations by training exclusively on the most perfectly matched audio-visual pairs, then conduct our systematic investigation into how this extreme alignment transforms perceptual model behavior across retrieval and generation tasks. The encoders under study fall into two main groups consisting of image-centric encoders that were pretrained using visual modalities as intermediary hubs for connecting modalities, and text-centric encoders that were pretrained with direct audio-language alignment. We first measure the baseline performance of these encoders on two key tasks, namely cross-modal retrieval and text description generation in vision-language models. Subsequently, we realign all encoders with the CLIP space using highly coherent audio-visual data and observe the performance changes. Our findings reveal that the initial architectural type of the encoder determines how it responds to the alignment process. Image-centric encoders, which are inherently designed for alignment, demonstrate exceptional performance in cross-modal retrieval, but this intensive alignment causes compression of unique linguistic information and reduces the quality of their text description generation in vision-language models. In contrast, text-centric encoders, which possess stronger linguistic authenticity, are able to maintain a better balance between the two objectives.

In this paper we propose a Sequential Representation Quantization AutoEncoder (SeqRQ-AE) to learn from primarily unpaired audio data and produce sequences of representations very close to phoneme sequences of speech utterances. This is achieved by proper temporal segmentation to make the representations phoneme-synchronized, and proper phonetic clustering to have total number of distinct representations close to the number of phonemes. Mapping between the distinct representations and phonemes is learned from a small amount of annotated paired data. Preliminary experiments on LJSpeech demonstrated the learned representations for vowels have relative locations in latent space in good parallel to that shown in the IPA vowel chart defined by linguistics experts. With less than 20 minutes of annotated speech, our method outperformed existing methods on phoneme recognition and is able to synthesize intelligible speech that beats our baseline model.

Neural audio codecs and autoencoders have emerged as versatile models for audio compression, transmission, feature-extraction, and latent-space generation. However, a key limitation is that most are trained to maximize reconstruction fidelity, often neglecting the specific latent structure necessary for optimal performance in diverse downstream applications. We propose a simple, post-hoc framework to address this by modifying the bottleneck of a pre-trained autoencoder. Our method introduces a "Re-Bottleneck", an inner bottleneck trained exclusively through latent space losses to instill user-defined structure. We demonstrate the framework's effectiveness in three experiments. First, we enforce an ordering on latent channels without sacrificing reconstruction quality. Second, we align latents with semantic embeddings, analyzing the impact on downstream diffusion modeling. Third, we introduce equivariance, ensuring that a filtering operation on the input waveform directly corresponds to a specific transformation in the latent space. Ultimately, our Re-Bottleneck framework offers a flexible and efficient way to tailor representations of neural audio models, enabling them to seamlessly meet the varied demands of different applications with minimal additional training.

Representing wild sounds as images is an important but challenging task due to the lack of paired datasets between sound and images and the significant differences in the characteristics of these two modalities. Previous studies have focused on generating images from sound in limited categories or music. In this paper, we propose a novel approach to generate images from in-the-wild sounds. First, we convert sound into text using audio captioning. Second, we propose audio attention and sentence attention to represent the rich characteristics of sound and visualize the sound. Lastly, we propose a direct sound optimization with CLIPscore and AudioCLIP and generate images with a diffusion-based model. In experiments, it shows that our model is able to generate high quality images from wild sounds and outperforms baselines in both quantitative and qualitative evaluations on wild audio datasets.

Audio is essential for multimodal video understanding. On the one hand, video inherently contains audio, which supplies complementary information to vision. Besides, video large language models (Video-LLMs) can encounter many audio-centric settings. However, existing Video-LLMs and Audio-Visual Large Language Models (AV-LLMs) exhibit deficiencies in exploiting audio information, leading to weak understanding and hallucinations. To solve the issues, we delve into the model architecture and dataset. (1) From the architectural perspective, we propose a fine-grained AV-LLM, namely Dolphin. The concurrent alignment of audio and visual modalities in both temporal and spatial dimensions ensures a comprehensive and accurate understanding of videos. Specifically, we devise an audio-visual multi-scale adapter for multi-scale information aggregation, which achieves spatial alignment. For temporal alignment, we propose audio-visual interleaved merging. (2) From the dataset perspective, we curate an audio-visual caption and instruction-tuning dataset, called AVU. It comprises 5.2 million diverse, open-ended data tuples (video, audio, question, answer) and introduces a novel data partitioning strategy. Extensive experiments show our model not only achieves remarkable performance in audio-visual understanding, but also mitigates potential hallucinations.

This paper presents a fascinating find: By training an auto-regressive LLM model on text tokens, the text model inherently develops internally an ability to understand images and audio, thereby developing the ability to see and hear just by reading. Popular audio and visual LLM models fine-tune text LLM models to give text output conditioned on images and audio embeddings. On the other hand, our architecture takes in patches of images, audio waveforms or tokens as input. It gives us the embeddings or category labels typical of a classification pipeline. We show the generality of text weights in aiding audio classification for datasets FSD-50K and GTZAN. Further, we show this working for image classification on CIFAR-10 and Fashion-MNIST, as well on image patches. This pushes the notion of text-LLMs learning powerful internal circuits that can be utilized by activating necessary connections for various applications rather than training models from scratch every single time.

We present two end-to-end models: Audio-to-Byte (A2B) and Byte-to-Audio (B2A), for multilingual speech recognition and synthesis. Prior work has predominantly used characters, sub-words or words as the unit of choice to model text. These units are difficult to scale to languages with large vocabularies, particularly in the case of multilingual processing. In this work, we model text via a sequence of Unicode bytes, specifically, the UTF-8 variable length byte sequence for each character. Bytes allow us to avoid large softmaxes in languages with large vocabularies, and share representations in multilingual models. We show that bytes are superior to grapheme characters over a wide variety of languages in monolingual end-to-end speech recognition. Additionally, our multilingual byte model outperform each respective single language baseline on average by 4.4% relatively. In Japanese-English code-switching speech, our multilingual byte model outperform our monolingual baseline by 38.6% relatively. Finally, we present an end-to-end multilingual speech synthesis model using byte representations which matches the performance of our monolingual baselines.

Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase, and (3) sound units have variable lengths with no explicit segmentation. To deal with these three problems, we propose the Hidden-Unit BERT (HuBERT) approach for self-supervised speech representation learning, which utilizes an offline clustering step to provide aligned target labels for a BERT-like prediction loss. A key ingredient of our approach is applying the prediction loss over the masked regions only, which forces the model to learn a combined acoustic and language model over the continuous inputs. HuBERT relies primarily on the consistency of the unsupervised clustering step rather than the intrinsic quality of the assigned cluster labels. Starting with a simple k-means teacher of 100 clusters, and using two iterations of clustering, the HuBERT model either matches or improves upon the state-of-the-art wav2vec 2.0 performance on the Librispeech (960h) and Libri-light (60,000h) benchmarks with 10min, 1h, 10h, 100h, and 960h fine-tuning subsets. Using a 1B parameter model, HuBERT shows up to 19% and 13% relative WER reduction on the more challenging dev-other and test-other evaluation subsets.

We propose Fast Language-Audio Pre-training (FLAP), a self-supervised approach that efficiently and effectively learns aligned audio and language representations through masking, contrastive learning and reconstruction. For efficiency, FLAP randomly drops audio spectrogram tokens, focusing solely on the remaining ones for self-supervision. Through inter-modal contrastive learning, FLAP learns to align paired audio and text representations in a shared latent space. Notably, FLAP leverages multiple augmented views via masking for inter-modal contrast and learns to reconstruct the masked portion of audio tokens. Moreover, FLAP leverages large language models (LLMs) to augment the text inputs, contributing to improved performance. These approaches lead to more robust and informative audio-text representations, enabling FLAP to achieve state-of-the-art (SoTA) performance on audio-text retrieval tasks on AudioCaps (achieving 53.0% R@1) and Clotho (achieving 25.5% R@1).

We introduce SPIRIT-LM, a foundation multimodal language model that freely mixes text and speech. Our model is based on a pretrained text language model that we extend to the speech modality by continuously training it on text and speech units. Speech and text sequences are concatenated as a single set of tokens, and trained with a word-level interleaving method using a small automatically-curated speech-text parallel corpus. SPIRIT-LM comes in two versions: a BASE version that uses speech semantic units and an EXPRESSIVE version that models expressivity using pitch and style units in addition to the semantic units. For both versions, the text is encoded with subword BPE tokens. The resulting model displays both the semantic abilities of text models and the expressive abilities of speech models. Additionally, we demonstrate that SPIRIT-LM is able to learn new tasks in a few-shot fashion across modalities (i.e. ASR, TTS, Speech Classification).

This survey paper provides a comprehensive overview of the recent advancements and challenges in applying large language models to the field of audio signal processing. Audio processing, with its diverse signal representations and a wide range of sources--from human voices to musical instruments and environmental sounds--poses challenges distinct from those found in traditional Natural Language Processing scenarios. Nevertheless, Large Audio Models, epitomized by transformer-based architectures, have shown marked efficacy in this sphere. By leveraging massive amount of data, these models have demonstrated prowess in a variety of audio tasks, spanning from Automatic Speech Recognition and Text-To-Speech to Music Generation, among others. Notably, recently these Foundational Audio Models, like SeamlessM4T, have started showing abilities to act as universal translators, supporting multiple speech tasks for up to 100 languages without any reliance on separate task-specific systems. This paper presents an in-depth analysis of state-of-the-art methodologies regarding Foundational Large Audio Models, their performance benchmarks, and their applicability to real-world scenarios. We also highlight current limitations and provide insights into potential future research directions in the realm of Large Audio Models with the intent to spark further discussion, thereby fostering innovation in the next generation of audio-processing systems. Furthermore, to cope with the rapid development in this area, we will consistently update the relevant repository with relevant recent articles and their open-source implementations at https://github.com/EmulationAI/awesome-large-audio-models.

Speech sounds convey a great deal of information about the scenes, resulting in a variety of effects ranging from reverberation to additional ambient sounds. In this paper, we manipulate input speech to sound as though it was recorded within a different scene, given an audio-visual conditional example recorded from that scene. Our model learns through self-supervision, taking advantage of the fact that natural video contains recurring sound events and textures. We extract an audio clip from a video and apply speech enhancement. We then train a latent diffusion model to recover the original speech, using another audio-visual clip taken from elsewhere in the video as a conditional hint. Through this process, the model learns to transfer the conditional example's sound properties to the input speech. We show that our model can be successfully trained using unlabeled, in-the-wild videos, and that an additional visual signal can improve its sound prediction abilities. Please see our project webpage for video results: https://tinglok.netlify.app/files/avsoundscape/

Instructional videos are an excellent source for learning multimodal representations by leveraging video-subtitle pairs extracted with automatic speech recognition systems (ASR) from the audio signal in the videos. However, in contrast to human-annotated captions, both speech and subtitles naturally differ from the visual content of the videos and thus provide only noisy supervision for multimodal learning. As a result, large-scale annotation-free web video training data remains sub-optimal for training text-video models. In this work, we propose to leverage the capability of large language models (LLMs) to obtain fine-grained video descriptions aligned with videos. Specifically, we prompt an LLM to create plausible video descriptions based on ASR narrations of the video for a large-scale instructional video dataset. To this end, we introduce a prompting method that is able to take into account a longer text of subtitles, allowing us to capture context beyond a single sentence. To align the captions to the video temporally, we prompt the LLM to generate timestamps for each produced caption based on the subtitles. In this way, we obtain human-style video captions at scale without human supervision. We apply our method to the subtitles of the HowTo100M dataset, creating a new large-scale dataset, HowToCaption. Our evaluation shows that the resulting captions not only significantly improve the performance over many different benchmark datasets for text-video retrieval but also lead to a disentangling of textual narration from the audio, boosting performance in text-video-audio tasks.

This paper presents an innovative approach to enhance control over audio generation by emphasizing the alignment between audio and text representations during model training. In the context of language model-based audio generation, the model leverages input from both textual and audio token representations to predict subsequent audio tokens. However, the current configuration lacks explicit regularization to ensure the alignment between the chosen text representation and the language model's predictions. Our proposal involves the incorporation of audio and text representation regularization, particularly during the classifier-free guidance (CFG) phase, where the text condition is excluded from cross attention during language model training. The aim of this proposed representation regularization is to minimize discrepancies in audio and text similarity compared to other samples within the same training batch. Experimental results on both music and audio generation tasks demonstrate that our proposed methods lead to improvements in objective metrics for both audio and music generation, as well as an enhancement in the human perception for audio generation.

Continual learning is a challenging problem in which models need to be trained on non-stationary data across sequential tasks for class-incremental learning. While previous methods have focused on using either regularization or rehearsal-based frameworks to alleviate catastrophic forgetting in image classification, they are limited to a single modality and cannot learn compact class-aware cross-modal representations for continual audio-visual learning. To address this gap, we propose a novel class-incremental grouping network (CIGN) that can learn category-wise semantic features to achieve continual audio-visual learning. Our CIGN leverages learnable audio-visual class tokens and audio-visual grouping to continually aggregate class-aware features. Additionally, it utilizes class tokens distillation and continual grouping to prevent forgetting parameters learned from previous tasks, thereby improving the model's ability to capture discriminative audio-visual categories. We conduct extensive experiments on VGGSound-Instruments, VGGSound-100, and VGG-Sound Sources benchmarks. Our experimental results demonstrate that the CIGN achieves state-of-the-art audio-visual class-incremental learning performance. Code is available at https://github.com/stoneMo/CIGN.

Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however remained an elusive problem. With a focus on text-to-speech synthesis, we describe a set of general techniques for reducing sampling time while maintaining high output quality. We first describe a single-layer recurrent neural network, the WaveRNN, with a dual softmax layer that matches the quality of the state-of-the-art WaveNet model. The compact form of the network makes it possible to generate 24kHz 16-bit audio 4x faster than real time on a GPU. Second, we apply a weight pruning technique to reduce the number of weights in the WaveRNN. We find that, for a constant number of parameters, large sparse networks perform better than small dense networks and this relationship holds for sparsity levels beyond 96%. The small number of weights in a Sparse WaveRNN makes it possible to sample high-fidelity audio on a mobile CPU in real time. Finally, we propose a new generation scheme based on subscaling that folds a long sequence into a batch of shorter sequences and allows one to generate multiple samples at once. The Subscale WaveRNN produces 16 samples per step without loss of quality and offers an orthogonal method for increasing sampling efficiency.

Current approaches to learning semantic representations of sentences often use prior word-level knowledge. The current study aims to leverage visual information in order to capture sentence level semantics without the need for word embeddings. We use a multimodal sentence encoder trained on a corpus of images with matching text captions to produce visually grounded sentence embeddings. Deep Neural Networks are trained to map the two modalities to a common embedding space such that for an image the corresponding caption can be retrieved and vice versa. We show that our model achieves results comparable to the current state-of-the-art on two popular image-caption retrieval benchmark data sets: MSCOCO and Flickr8k. We evaluate the semantic content of the resulting sentence embeddings using the data from the Semantic Textual Similarity benchmark task and show that the multimodal embeddings correlate well with human semantic similarity judgements. The system achieves state-of-the-art results on several of these benchmarks, which shows that a system trained solely on multimodal data, without assuming any word representations, is able to capture sentence level semantics. Importantly, this result shows that we do not need prior knowledge of lexical level semantics in order to model sentence level semantics. These findings demonstrate the importance of visual information in semantics.

Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U, short for wav2vec Unsupervised, a method to train speech recognition models without any labeled data. We leverage self-supervised speech representations to segment unlabeled audio and learn a mapping from these representations to phonemes via adversarial training. The right representations are key to the success of our method. Compared to the best previous unsupervised work, wav2vec-U reduces the phoneme error rate on the TIMIT benchmark from 26.1 to 11.3. On the larger English Librispeech benchmark, wav2vec-U achieves a word error rate of 5.9 on test-other, rivaling some of the best published systems trained on 960 hours of labeled data from only two years ago. We also experiment on nine other languages, including low-resource languages such as Kyrgyz, Swahili and Tatar.

We introduce Noise2Music, where a series of diffusion models is trained to generate high-quality 30-second music clips from text prompts. Two types of diffusion models, a generator model, which generates an intermediate representation conditioned on text, and a cascader model, which generates high-fidelity audio conditioned on the intermediate representation and possibly the text, are trained and utilized in succession to generate high-fidelity music. We explore two options for the intermediate representation, one using a spectrogram and the other using audio with lower fidelity. We find that the generated audio is not only able to faithfully reflect key elements of the text prompt such as genre, tempo, instruments, mood, and era, but goes beyond to ground fine-grained semantics of the prompt. Pretrained large language models play a key role in this story -- they are used to generate paired text for the audio of the training set and to extract embeddings of the text prompts ingested by the diffusion models. Generated examples: https://google-research.github.io/noise2music

Open-vocabulary audio-language models, like CLAP, offer a promising approach for zero-shot audio classification (ZSAC) by enabling classification with any arbitrary set of categories specified with natural language prompts. In this paper, we propose a simple but effective method to improve ZSAC with CLAP. Specifically, we shift from the conventional method of using prompts with abstract category labels (e.g., Sound of an organ) to prompts that describe sounds using their inherent descriptive features in a diverse context (e.g.,The organ's deep and resonant tones filled the cathedral.). To achieve this, we first propose ReCLAP, a CLAP model trained with rewritten audio captions for improved understanding of sounds in the wild. These rewritten captions describe each sound event in the original caption using their unique discriminative characteristics. ReCLAP outperforms all baselines on both multi-modal audio-text retrieval and ZSAC. Next, to improve zero-shot audio classification with ReCLAP, we propose prompt augmentation. In contrast to the traditional method of employing hand-written template prompts, we generate custom prompts for each unique label in the dataset. These custom prompts first describe the sound event in the label and then employ them in diverse scenes. Our proposed method improves ReCLAP's performance on ZSAC by 1%-18% and outperforms all baselines by 1% - 55%.

We present ImageBind, an approach to learn a joint embedding across six different modalities - images, text, audio, depth, thermal, and IMU data. We show that all combinations of paired data are not necessary to train such a joint embedding, and only image-paired data is sufficient to bind the modalities together. ImageBind can leverage recent large scale vision-language models, and extends their zero-shot capabilities to new modalities just by using their natural pairing with images. It enables novel emergent applications 'out-of-the-box' including cross-modal retrieval, composing modalities with arithmetic, cross-modal detection and generation. The emergent capabilities improve with the strength of the image encoder and we set a new state-of-the-art on emergent zero-shot recognition tasks across modalities, outperforming specialist supervised models. Finally, we show strong few-shot recognition results outperforming prior work, and that ImageBind serves as a new way to evaluate vision models for visual and non-visual tasks.

Multimodal models have demonstrated powerful capabilities in complex tasks requiring multimodal alignment including zero-shot classification and cross-modal retrieval. However, existing models typically rely on millions of paired multimodal samples, which are prohibitively expensive or infeasible to obtain in many domains. In this work, we explore the feasibility of building multimodal models with limited amount of paired data by aligning pretrained unimodal foundation models. We show that high-quality alignment is possible with as few as tens of thousands of paired samplesx2013less than 1% of the data typically used in the field. To achieve this, we introduce STRUCTURE, an effective regularization technique that preserves the neighborhood geometry of the latent space of unimodal encoders. Additionally, we show that aligning last layers is often suboptimal and demonstrate the benefits of aligning the layers with the highest representational similarity across modalities. These two components can be readily incorporated into existing alignment methods, yielding substantial gains across 24 zero-shot image classification and retrieval benchmarks, with average relative improvement of 51.6% in classification and 91.8% in retrieval tasks. Our results highlight the effectiveness and broad applicability of our framework for limited-sample multimodal learning and offer a promising path forward for resource-constrained domains.

Human perception integrates multiple modalities, such as vision, hearing, and language, into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligning pairs of modalities via contrastive learning, their solutions are unsuitable when scaling to multiple modalities. These models typically align each modality to a designated anchor without ensuring the alignment of all modalities with each other, leading to suboptimal performance in tasks requiring a joint understanding of multiple modalities. In this paper, we structurally rethink the pairwise conventional approach to multimodal learning and we present the novel Gramian Representation Alignment Measure (GRAM), which overcomes the above-mentioned limitations. GRAM learns and then aligns n modalities directly in the higher-dimensional space in which modality embeddings lie by minimizing the Gramian volume of the k-dimensional parallelotope spanned by the modality vectors, ensuring the geometric alignment of all modalities simultaneously. GRAM can replace cosine similarity in any downstream method, holding for 2 to n modalities and providing more meaningful alignment with respect to previous similarity measures. The novel GRAM-based contrastive loss function enhances the alignment of multimodal models in the higher-dimensional embedding space, leading to new state-of-the-art performance in downstream tasks such as video-audio-text retrieval and audio-video classification. The project page, the code, and the pretrained models are available at https://ispamm.github.io/GRAM/.

Sound event detection (SED) often suffers from the data deficiency problem. The recent baseline system in the DCASE2023 challenge task 4 leverages the large pretrained self-supervised learning (SelfSL) models to mitigate such restriction, where the pretrained models help to produce more discriminative features for SED. However, the pretrained models are regarded as a frozen feature extractor in the challenge baseline system and most of the challenge submissions, and fine-tuning of the pretrained models has been rarely studied. In this work, we study the fine-tuning method of the pretrained models for SED. We first introduce ATST-Frame, our newly proposed SelfSL model, to the SED system. ATST-Frame was especially designed for learning frame-level representations of audio signals and obtained state-of-the-art (SOTA) performances on a series of downstream tasks. We then propose a fine-tuning method for ATST-Frame using both (in-domain) unlabelled and labelled SED data. Our experiments show that, the proposed method overcomes the overfitting problem when fine-tuning the large pretrained network, and our SED system obtains new SOTA results of 0.587/0.812 PSDS1/PSDS2 scores on the DCASE challenge task 4 dataset.

The goal of the Acoustic Question Answering (AQA) task is to answer a free-form text question about the content of an acoustic scene. It was inspired by the Visual Question Answering (VQA) task. In this paper, based on the previously introduced CLEAR dataset, we propose a new benchmark for AQA, namely CLEAR2, that emphasizes the specific challenges of acoustic inputs. These include handling of variable duration scenes, and scenes built with elementary sounds that differ between training and test set. We also introduce NAAQA, a neural architecture that leverages specific properties of acoustic inputs. The use of 1D convolutions in time and frequency to process 2D spectro-temporal representations of acoustic content shows promising results and enables reductions in model complexity. We show that time coordinate maps augment temporal localization capabilities which enhance performance of the network by ~17 percentage points. On the other hand, frequency coordinate maps have little influence on this task. NAAQA achieves 79.5% of accuracy on the AQA task with ~4 times fewer parameters than the previously explored VQA model. We evaluate the perfomance of NAAQA on an independent data set reconstructed from DAQA. We also test the addition of a MALiMo module in our model on both CLEAR2 and DAQA. We provide a detailed analysis of the results for the different question types. We release the code to produce CLEAR2 as well as NAAQA to foster research in this newly emerging machine learning task.

In the past, the rapidly evolving field of sound classification greatly benefited from the application of methods from other domains. Today, we observe the trend to fuse domain-specific tasks and approaches together, which provides the community with new outstanding models. In this work, we present an extension of the CLIP model that handles audio in addition to text and images. Our proposed model incorporates the ESResNeXt audio-model into the CLIP framework using the AudioSet dataset. Such a combination enables the proposed model to perform bimodal and unimodal classification and querying, while keeping CLIP's ability to generalize to unseen datasets in a zero-shot inference fashion. AudioCLIP achieves new state-of-the-art results in the Environmental Sound Classification (ESC) task, out-performing other approaches by reaching accuracies of 90.07% on the UrbanSound8K and 97.15% on the ESC-50 datasets. Further it sets new baselines in the zero-shot ESC-task on the same datasets (68.78% and 69.40%, respectively). Finally, we also assess the cross-modal querying performance of the proposed model as well as the influence of full and partial training on the results. For the sake of reproducibility, our code is published.

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up the training by using a single multiscale spectrogram adversary that efficiently reduces artifacts and produce high-quality samples. We introduce a novel loss balancer mechanism to stabilize training: the weight of a loss now defines the fraction of the overall gradient it should represent, thus decoupling the choice of this hyper-parameter from the typical scale of the loss. Finally, we study how lightweight Transformer models can be used to further compress the obtained representation by up to 40%, while staying faster than real time. We provide a detailed description of the key design choices of the proposed model including: training objective, architectural changes and a study of various perceptual loss functions. We present an extensive subjective evaluation (MUSHRA tests) together with an ablation study for a range of bandwidths and audio domains, including speech, noisy-reverberant speech, and music. Our approach is superior to the baselines methods across all evaluated settings, considering both 24 kHz monophonic and 48 kHz stereophonic audio. Code and models are available at github.com/facebookresearch/encodec.

Can we leverage the audiovisual information already present in video to improve self-supervised representation learning? To answer this question, we study various pretraining architectures and objectives within the masked autoencoding framework, motivated by the success of similar methods in natural language and image understanding. We show that we can achieve significant improvements on audiovisual downstream classification tasks, surpassing the state-of-the-art on VGGSound and AudioSet. Furthermore, we can leverage our audiovisual pretraining scheme for multiple unimodal downstream tasks using a single audiovisual pretrained model. We additionally demonstrate the transferability of our representations, achieving state-of-the-art audiovisual results on Epic Kitchens without pretraining specifically for this dataset.

Multi-modal large language models are regarded as a crucial step towards Artificial General Intelligence (AGI) and have garnered significant interest with the emergence of ChatGPT. However, current speech-language models typically adopt the cascade paradigm, preventing inter-modal knowledge transfer. In this paper, we propose SpeechGPT, a large language model with intrinsic cross-modal conversational abilities, capable of perceiving and generating multi-model content. With discrete speech representations, we first construct SpeechInstruct, a large-scale cross-modal speech instruction dataset. Additionally, we employ a three-stage training strategy that includes modality-adaptation pre-training, cross-modal instruction fine-tuning, and chain-of-modality instruction fine-tuning. The experimental results demonstrate that SpeechGPT has an impressive capacity to follow multi-modal human instructions and highlight the potential of handling multiple modalities with one model. Demos are shown in https://0nutation.github.io/SpeechGPT.github.io/.

We propose EnCLAP, a novel framework for automated audio captioning. EnCLAP employs two acoustic representation models, EnCodec and CLAP, along with a pretrained language model, BART. We also introduce a new training objective called masked codec modeling that improves acoustic awareness of the pretrained language model. Experimental results on AudioCaps and Clotho demonstrate that our model surpasses the performance of baseline models. Source code will be available at https://github.com/jaeyeonkim99/EnCLAP . An online demo is available at https://huggingface.co/spaces/enclap-team/enclap .

Diffusion models have achieved state-of-the-art synthesis quality on both visual and audio tasks, and recent works further adapt them to textual data by diffusing on the embedding space. In this paper, we conduct systematic studies and analyze the challenges between the continuous data space and the embedding space which have not been carefully explored. Firstly, the data distribution is learnable for embeddings, which may lead to the collapse of the loss function. Secondly, as the norm of embeddings varies between popular and rare words, adding the same noise scale will lead to sub-optimal results. In addition, we find the normal level of noise causes insufficient training of the model. To address the above challenges, we propose Difformer, an embedding diffusion model based on Transformer, which consists of three essential modules including an additional anchor loss function, a layer normalization module for embeddings, and a noise factor to the Gaussian noise. Experiments on two seminal text generation tasks including machine translation and text summarization show the superiority of Difformer over compared embedding diffusion baselines.

This paper introduces ESPnet-SPK, a toolkit designed with several objectives for training speaker embedding extractors. First, we provide an open-source platform for researchers in the speaker recognition community to effortlessly build models. We provide several models, ranging from x-vector to recent SKA-TDNN. Through the modularized architecture design, variants can be developed easily. We also aspire to bridge developed models with other domains, facilitating the broad research community to effortlessly incorporate state-of-the-art embedding extractors. Pre-trained embedding extractors can be accessed in an off-the-shelf manner and we demonstrate the toolkit's versatility by showcasing its integration with two tasks. Another goal is to integrate with diverse self-supervised learning features. We release a reproducible recipe that achieves an equal error rate of 0.39% on the Vox1-O evaluation protocol using WavLM-Large with ECAPA-TDNN.

We present ParrotTTS, a modularized text-to-speech synthesis model leveraging disentangled self-supervised speech representations. It can train a multi-speaker variant effectively using transcripts from a single speaker. ParrotTTS adapts to a new language in low resource setup and generalizes to languages not seen while training the self-supervised backbone. Moreover, without training on bilingual or parallel examples, ParrotTTS can transfer voices across languages while preserving the speaker specific characteristics, e.g., synthesizing fluent Hindi speech using a French speaker's voice and accent. We present extensive results in monolingual and multi-lingual scenarios. ParrotTTS outperforms state-of-the-art multi-lingual TTS models using only a fraction of paired data as latter.

Text-to-speech models trained on large-scale datasets have demonstrated impressive in-context learning capabilities and naturalness. However, control of speaker identity and style in these models typically requires conditioning on reference speech recordings, limiting creative applications. Alternatively, natural language prompting of speaker identity and style has demonstrated promising results and provides an intuitive method of control. However, reliance on human-labeled descriptions prevents scaling to large datasets. Our work bridges the gap between these two approaches. We propose a scalable method for labeling various aspects of speaker identity, style, and recording conditions. We then apply this method to a 45k hour dataset, which we use to train a speech language model. Furthermore, we propose simple methods for increasing audio fidelity, significantly outperforming recent work despite relying entirely on found data. Our results demonstrate high-fidelity speech generation in a diverse range of accents, prosodic styles, channel conditions, and acoustic conditions, all accomplished with a single model and intuitive natural language conditioning. Audio samples can be heard at https://text-description-to-speech.com/.

We tackle the problem of generating audio samples conditioned on descriptive text captions. In this work, we propose AaudioGen, an auto-regressive generative model that generates audio samples conditioned on text inputs. AudioGen operates on a learnt discrete audio representation. The task of text-to-audio generation poses multiple challenges. Due to the way audio travels through a medium, differentiating ``objects'' can be a difficult task (e.g., separating multiple people simultaneously speaking). This is further complicated by real-world recording conditions (e.g., background noise, reverberation, etc.). Scarce text annotations impose another constraint, limiting the ability to scale models. Finally, modeling high-fidelity audio requires encoding audio at high sampling rate, leading to extremely long sequences. To alleviate the aforementioned challenges we propose an augmentation technique that mixes different audio samples, driving the model to internally learn to separate multiple sources. We curated 10 datasets containing different types of audio and text annotations to handle the scarcity of text-audio data points. For faster inference, we explore the use of multi-stream modeling, allowing the use of shorter sequences while maintaining a similar bitrate and perceptual quality. We apply classifier-free guidance to improve adherence to text. Comparing to the evaluated baselines, AudioGen outperforms over both objective and subjective metrics. Finally, we explore the ability of the proposed method to generate audio continuation conditionally and unconditionally. Samples: https://felixkreuk.github.io/audiogen

We present MELLE, a novel continuous-valued tokens based language modeling approach for text to speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for vector quantization, which are originally designed for audio compression and sacrifice fidelity compared to mel-spectrograms. Specifically, (i) instead of cross-entropy loss, we apply regression loss with a proposed spectrogram flux loss function to model the probability distribution of the continuous-valued tokens. (ii) we have incorporated variational inference into MELLE to facilitate sampling mechanisms, thereby enhancing the output diversity and model robustness. Experiments demonstrate that, compared to the two-stage codec language models VALL-E and its variants, the single-stage MELLE mitigates robustness issues by avoiding the inherent flaws of sampling discrete codes, achieves superior performance across multiple metrics, and, most importantly, offers a more streamlined paradigm. See https://aka.ms/melle for demos of our work.

Recent advances in large language models, particularly following GPT-4o, have sparked increasing interest in developing omni-modal models capable of understanding more modalities. While some open-source alternatives have emerged, there is still a notable lag behind specialized single-modality models in performance. In this paper, we present Ola, an Omni-modal language model that achieves competitive performance across image, video, and audio understanding compared to specialized counterparts. The core design of Ola lies in its progressive modality alignment strategy that extends the supporting modality of the language model progressively. Our training pipeline begins with the most distinct modalities: image and text, then gradually expands the skill sets of the model using speech data that connects language and audio knowledge, and video data that connects all modalities. The progressive learning pipeline also enables us to maintain a relatively small size of the cross-modal alignment data, making developing omni-modal from existing vision-language models easy and less costly. Moreover, to unlock an advanced interactive experience like GPT-4o, we further design a sentence-wise decoding solution for streaming speech generation. Extensive experiments demonstrate that Ola surpasses existing open omni-modal LLMs across all modalities while achieving highly competitive performance compared to state-of-the-art specialized models of similar sizes. We aim to make Ola a fully open omni-modal understanding solution to advance future research in this emerging field. Model weights, code, and data are open-sourced at https://github.com/Ola-Omni/Ola.

Visual Speech Recognition (VSR) differs from the common perception tasks as it requires deeper reasoning over the video sequence, even by human experts. Despite the recent advances in VSR, current approaches rely on labeled data to fully train or finetune their models predicting the target speech. This hinders their ability to generalize well beyond the training set and leads to performance degeneration under out-of-distribution challenging scenarios. Unlike previous works that involve auxiliary losses or complex training procedures and architectures, we propose a simple approach, named Lip2Vec that is based on learning a prior model. Given a robust visual speech encoder, this network maps the encoded latent representations of the lip sequence to their corresponding latents from the audio pair, which are sufficiently invariant for effective text decoding. The generated audio representation is then decoded to text using an off-the-shelf Audio Speech Recognition (ASR) model. The proposed model compares favorably with fully-supervised learning methods on the LRS3 dataset achieving 26 WER. Unlike SoTA approaches, our model keeps a reasonable performance on the VoxCeleb test set. We believe that reprogramming the VSR as an ASR task narrows the performance gap between the two and paves the way for more flexible formulations of lip reading.