Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
# Overview
|
| 2 |
Official implementation of IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE/ACM TASLP) 2024 paper **"[DeFTAN-II: Efficient multichannel speech enhancement with subgroup processing](https://arxiv.org/pdf/2308.15777) (accepted)"**.
|
|
|
|
| 3 |
|
| 4 |
The abstract from the paper is the following:
|
| 5 |
|
|
@@ -10,7 +11,7 @@ The abstract from the paper is the following:
|
|
| 10 |
We uploaded a pre-trained model trained on the spatialized DNS challenge dataset to Hugging Face.
|
| 11 |
|
| 12 |
|
| 13 |
-
## Using pre-trained model
|
| 14 |
Download `deftan-II.py` and `max.pt` to `your\path\`.
|
| 15 |
You may import the DeFTAN-II class and load the `state_dict` using the code below.
|
| 16 |
|
|
|
|
| 1 |
# Overview
|
| 2 |
Official implementation of IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE/ACM TASLP) 2024 paper **"[DeFTAN-II: Efficient multichannel speech enhancement with subgroup processing](https://arxiv.org/pdf/2308.15777) (accepted)"**.
|
| 3 |
+
[<a href="https://arxiv.org/pdf/2308.15777.pdf" target="_blank">Paper</a> | <a href="https://github.com/donghoney0416/DeFTAN-II/tree/main" target="_blank">Code</a> | <a href="https://donghoney0416.github.io/demos-DeFTAN-II/demo-page.html" target="blank">Demo</a>]
|
| 4 |
|
| 5 |
The abstract from the paper is the following:
|
| 6 |
|
|
|
|
| 11 |
We uploaded a pre-trained model trained on the spatialized DNS challenge dataset to Hugging Face.
|
| 12 |
|
| 13 |
|
| 14 |
+
## Using pre-trained model (spatialized DNS challenge dataset)
|
| 15 |
Download `deftan-II.py` and `max.pt` to `your\path\`.
|
| 16 |
You may import the DeFTAN-II class and load the `state_dict` using the code below.
|
| 17 |
|