search

Audio-WestlakeU / FullSubNet

PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."
https://fullsubnet.readthedocs.io/en/latest/
MIT License
538 stars 153 forks source link

Sub-band model #28

Closed HWLhsu closed 2 years ago

HWLhsu commented 3 years ago

Hi, thanks for sharing this excellent project. I took a great interest in the model(Delayed Sub-Band LSTM) posted in the paper. I've tried my hard to reproduce this model, but still can't get a well performance. Can you release the code about your sub-band models ? Thanks a lot!

haoxiangsnr commented 3 years ago

Hi, thanks for your attention. I haven't enough time to update the code of the delayed sub-band LSTM recently.

But you could attempt to delete the code corresponding to the full-band model in the FullSubNet project retaining the code about the cIRM and the training processing. Then you will get the delayed sub-band LSTM.

HWLhsu commented 3 years ago

OK, I'll try it. Thanks for your advice.