Skip to content

The PyTorch-based audio source separation toolkit for researchers

License

Notifications You must be signed in to change notification settings

iput2021-someya/asteroid

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

84 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Asteroid : Audio Source Separation on steroids

Why Asteroid ?

Audio source separation and speech enhancement are fast evolving fields with a growing number of papers submitted to conferences each year. While datasets such as wsj0-{2, 3}mix, WHAM or MS-SNSD are being shared, there has been little effort to create common codebases for development and evaluation of source separation and speech enhancement algorithms. Hence AsSteroid !

The intent of Asteroid is to be a community-based project, to go beyond sharing datasets. We share tools to create new algorithms as well as recipes to reproduce published papers.

Guiding principles

  • User friendliness.
  • Modularity.
  • Extensibility.
  • Reproducibility.

Recipes

Filterbanks

Analysis-synthesis

Analysis only (can be extended)

Running a recipe

Writing your own recipe

Contributing

Reproducibility

Make table with all the results per dataset here.

About

The PyTorch-based audio source separation toolkit for researchers

Resources

License

Code of conduct

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Jupyter Notebook 98.7%
  • Python 1.1%
  • Shell 0.2%