/FullSubNet

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

Primary LanguagePythonMIT LicenseMIT

FullSubNet

Platform Python version Pytorch Version GitHub repo size

This Git repository for the official PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement", accepted to ICASSP 2021.

💡[Demo] | 📄[PDF] | 💾[Model Checkpoint] | 📡[Loss Curve]

Introduction

Click it to show a video

Key Features

You can use all of these things:

  • Available models

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

  • Available datasets

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

Documentation

Citation

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

@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

License: MIT