|
|
|
language: en
|
|
tags:
|
|
- speech-enhancement
|
|
- dereverberation
|
|
- diffusion-models
|
|
- generative-models
|
|
- pytorch
|
|
- audio-processing
|
|
license: mit
|
|
datasets:
|
|
- VoiceBank-DEMAND
|
|
- WSJ0-CHiME3
|
|
- WSJ0-REVERB
|
|
- EARS-WHAM
|
|
- EARS-Reverb
|
|
model_name: speech-enhancement-dereverberation-diffusion
|
|
model_type: diffusion-based-generative-model
|
|
library_name: pytorch
|
|
pipeline_tag: audio-to-audio
|
|
|
|
|
|
key_files:
|
|
- model.py
|
|
- train.py
|
|
- inference.py
|
|
- enhancement.py
|
|
- requirements.txt
|
|
- calc_metrics.py
|
|
|
|
|
|
pretrained_checkpoints:
|
|
voicebank_demand:
|
|
description: SGMSE+ trained on VoiceBank-DEMAND
|
|
download_link: https://drive.google.com/drive/folders/1CSnkhUSoiv3RG0xg7WEcVapyLuwDaLbe?usp=sharing
|
|
gdown_id: 1_H3EXvhcYBhOZ9QNUcD5VZHc6ktrRbwQ
|
|
wsj0_chime3:
|
|
description: SGMSE+ trained on WSJ0-CHiME3
|
|
download_link: https://drive.google.com/drive/folders/1CSnkhUSoiv3RG0xg7WEcVapyLuwDaLbe?usp=sharing
|
|
gdown_id: 16K4DUdpmLhDNC7pJhBBc08pkSIn_yMPi
|
|
wsj0_reverb:
|
|
description: SGMSE+ trained on WSJ0-REVERB
|
|
download_link: https://drive.google.com/drive/folders/1082_PSEgrqoVVrNsAkSIcpLF1AAtzGwV?usp=sharing
|
|
gdown_id: 1eiOy0VjHh9V9ZUFTxu1Pq2w19izl9ejD
|
|
ears_wham:
|
|
description: SGMSE+ trained on EARS-WHAM
|
|
download_link: https://drive.google.com/drive/folders/1Tn6pVwjxUAy1DJ8167JCg3enuSi0hiw5?usp=sharing
|
|
gdown_id: 1t_DLLk8iPH6nj8M5wGeOP3jFPaz3i7K5
|
|
ears_reverb:
|
|
description: SGMSE+ trained on EARS-Reverb
|
|
download_link: https://drive.google.com/drive/folders/1PunXuLbuyGkknQCn_y-RCV2dTZBhyE3V?usp=sharing
|
|
gdown_id: 1PunXuLbuyGkknQCn_y-RCV2dTZBhyE3V
|
|
|
|
|
|
citations:
|
|
- '@inproceedings{welker22speech, author={Simon Welker and Julius Richter and Timo Gerkmann}, title={Speech Enhancement with Score-Based Generative Models in the Complex {STFT} Domain}, year={2022}, booktitle={Proc. Interspeech 2022}, pages={2928--2932}, doi={10.21437/Interspeech.2022-10653}}'
|
|
- '@article{richter2023speech, title={Speech Enhancement and Dereverberation with Diffusion-based Generative Models}, author={Richter, Julius and Welker, Simon and Lemercier, Jean-Marie and Lay, Bunlong and Gerkmann, Timo}, journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, volume={31}, pages={2351-2364}, year={2023}, doi={10.1109/TASLP.2023.3285241}}'
|
|
- '@inproceedings{richter2024ears, title={{EARS}: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation}, author={Richter, Julius and Wu, Yi-Chiao and Krenn, Steven and Welker, Simon and Lay, Bunlong and Watanabe, Shinjii and Richard, Alexander and Gerkmann, Timo}, booktitle={ISCA Interspeech}, year={2024}}'
|
|
|
