|
--- |
|
license: mit |
|
pipeline_tag: audio-to-audio |
|
tags: |
|
- denoising |
|
- speech enhancement |
|
- speech separation |
|
- noise suppression |
|
- realtime |
|
--- |
|
|
|
This is a pre-trained version of Fast FullSubNet, a real-time denoising model trained on the Deep Noise Suppression Challenge dataset of 2020 ([DNS-INTERSPEECH-2020](https://github.com/microsoft/DNS-Challenge/tree/interspeech2020/master)). |
|
|
|
## How to run |
|
|
|
https://fullsubnet.readthedocs.io/en/latest/usage/getting_started.html |
|
|
|
## Code |
|
|
|
https://github.com/Audio-WestlakeU/FullSubNet |
|
|
|
Note: The code doesn't support real-time streaming out of the box. See [issue-67](https://github.com/Audio-WestlakeU/FullSubNet/issues/67) for details. |
|
|
|
## Paper |
|
|
|
[Fast FullSubNet: Accelerate Full-band and Sub-band Fusion Model for Single-channel Speech Enhancement](https://arxiv.org/abs/2212.09019), Xiang Hao, Xiaofei Li |
|
|
|
> For many speech enhancement applications, a key feature is that system runs on a real-time, latency-sensitive, battery-powered platform, which strictly limits the algorithm latency and computational complexity. In this work, we propose a new architecture named Fast FullSubNet dedicated to accelerating the computation of FullSubNet. Specifically, Fast FullSubNet processes sub-band speech spectra in the mel-frequency domain by using cascaded linear-to-mel full-band, sub-band, and mel-to-linear full-band models such that frequencies involved in the sub-band computation are vastly reduced. After that, a down-sampling operation is proposed for the sub-band input sequence to further reduce the computational complexity along the time axis. Experimental results show that, compared to FullSubNet, Fast FullSubNet has only 13\% computational complexity and 16\% processing time, and achieves comparable or even better performance. |
|
|
|
## Performance |
|
|
|
| | With Reverb | | | | No Reverb | | | |
|
-- | -- | -- | -- | -- | -- | -- | -- |
|
Method | WB-PESQ | NB-PESQ | SI-SDR | STOI | WB-PESQ | NB-PESQ | SI-SDR | STOI |
|
Fast FullSubNet (118 Epochs) | 2.882 | 3.42 | 15.33 | 0.9233 | 2.694 | 3.222 | 16.34 | 0.9571 |
|
[FullSubNet (58 Epochs)](https://github.com/Audio-WestlakeU/FullSubNet/releases/tag/v0.2) (just for comparison) | 2.987 | 3.496 | 15.756 | 0.926 | 2.889 | 3.385 | 17.635 | 0.964 |
