Machine Learning

Self-Supervised Learning for General-Purpose Audio Representation

BYOL for Audio

This is a demo implementation of BYOL for Audio (BYOL-A), a self-supervised learning method for general-purpose audio representation, includes:

  • Training code that can train models with arbitrary audio files.
  • Evaluation code that can evaluate trained models with downstream tasks.
  • Pretrained weights.

If you find BYOL-A useful in your research, please use the following BibTeX entry for citation.

@misc{niizumi2021byol-a,
      title={BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation}, 
      author={Daisuke Niizumi and Daiki Takeuchi and Yasunori Ohishi and Noboru Harada and Kunio Kashino},
      booktitle = {2021 International Joint Conference on Neural Networks, {IJCNN} 2021},
      year={2021},
      eprint={2103.06695},
      archivePrefix={arXiv},
      primaryClass={eess.AS}
}

Getting Started

  1. Download external source files, and apply a patch. Our implementation uses the following.

    curl -O https://raw.githubusercontent.com/lucidrains/byol-pytorch/2aa84ee18fafecaf35637da4657f92619e83876d/byol_pytorch/byol_pytorch.py
    
patch < byol_a/byol_pytorch.diff
mv

 

 


    

     
    

    To finish reading, please visit source site