FullSubNet

Official PyTorch implementation of FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement, ICASSP 2021.

Guides

• 📰 Paper (PDF)
• 📸 Demo (Audio Clips)
• 📖 Documentation
• 🎏 Model Checkpoints
• 📹 Presentation (YouTube)

Key Features

You can use all of these things:

• Available models

  • [x] Fullband Baseline
  • [x] FullSubNet
  • [ ] FullSubNet (lightweight)
  • [ ] Delayed Sub-Band LSTM

• Available datasets

  • [x] Deep Noise Suppression Challenge - INTERSPEECH 2020
  • [ ] Demand + CSTR VCTK Corpus

Citation

If you use this code for your research, please consider citeing:

@INPROCEEDINGS{hao2020fullsubnet,
    author={Hao, Xiang and Su, Xiangdong and Horaud, Radu and Li, Xiaofei},
    booktitle={ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    title={Fullsubnet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement},
    year={2021},
    pages={6633-6637},
    doi={10.1109/ICASSP39728.2021.9414177}
}

License

This respository Under the MIT license.