Sepformer Wham16k Enhancement

🚀 SepFormer trained on WHAM! for speech enhancement (16k sampling frequency)

This repository offers tools for speech enhancement using a SepFormer model implemented with SpeechBrain and pretrained on the WHAM! dataset at 16k sampling frequency. The model achieves 14.3 dB SI - SNR on the WHAM! test set.

🚀 Quick Start

This repository provides all the necessary tools to perform speech enhancement (denoising) with a SepFormer model, implemented with SpeechBrain, and pretrained on WHAM! dataset with 16k sampling frequency, which is basically a version of WSJ0 - Mix dataset with environmental noise and reverberation in 8k. For a better experience we encourage you to learn more about SpeechBrain. The given model performance is 14.3 dB SI - SNR on the test set of WHAM! dataset.

📦 Installation

Install SpeechBrain

First of all, please install SpeechBrain with the following command:

pip install speechbrain

💡 Usage Tip

Please notice that we encourage you to read our tutorials and learn more about SpeechBrain.

💻 Usage Examples

Basic Usage

Perform speech enhancement on your own audio file

from speechbrain.pretrained import SepformerSeparation as separator
import torchaudio

model = separator.from_hparams(source="speechbrain/sepformer-wham16k-enhancement", savedir='pretrained_models/sepformer-wham16k-enhancement')

# for custom file, change path
est_sources = model.separate_file(path='speechbrain/sepformer-wham16k-enhancement/example_wham16k.wav') 

torchaudio.save("enhanced_wham16k.wav", est_sources[:, :, 0].detach().cpu(), 16000)

Advanced Usage

Inference on GPU

To perform inference on the GPU, add run_opts={"device":"cuda"} when calling the from_hparams method.

🔧 Technical Details

Training

The training script is currently being worked on an ongoing pull - request.

We will update the model card as soon as the PR is merged.

You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/1bbQvaiN - R79M697NnekA7Rr0jIYtO6e3).

Limitations

⚠️ Important Note

The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.

📚 Documentation

Referencing SpeechBrain

@misc{speechbrain,
  title={{SpeechBrain}: A General - Purpose Speech Toolkit},
  author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju - Chieh Chou and Sung - Lin Yeh and Szu - Wei Fu and Chien - Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
  year={2021},
  eprint={2106.04624},
  archivePrefix={arXiv},
  primaryClass={eess.AS},
  note={arXiv:2106.04624}
}

Referencing SepFormer

@inproceedings{subakan2021attention,
      title={Attention is All You Need in Speech Separation}, 
      author={Cem Subakan and Mirco Ravanelli and Samuele Cornell and Mirko Bronzi and Jianyuan Zhong},
      year={2021},
      booktitle={ICASSP 2021}
}

@article{subakan2023exploring,
  author={Subakan, Cem and Ravanelli, Mirco and Cornell, Samuele and Grondin, François and Bronzi, Mirko},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, 
  title={Exploring Self - Attention Mechanisms for Speech Separation}, 
  year={2023},
  volume={31},
  pages={2169 - 2180},
}

📄 License

The license for this project is apache - 2.0.

About SpeechBrain

• Website: https://speechbrain.github.io/
• Code: https://github.com/speechbrain/speechbrain/
• HuggingFace: https://huggingface.co/speechbrain/