Asteroid: The PyTorch-Based Audio Source Separation Toolkit for Researchers

Manuel Pariente, Samuele Cornell, Joris Cosentino, Sunit Sivasankaran, Efthymios Tzinis, Jens Heitkaemper, Michel Olvera, Fabian-Robert Stöter, Mathieu Hu, Juan M. Martín-Doñas, David Ditter, Ariel Frank, Antoine Deleforge, Emmanuel Vincent

This paper describes Asteroid, the PyTorch-based audio source separation toolkit for researchers. Inspired by the most successful neural source separation systems, it provides all neural building blocks required to build such a system. To improve reproducibility, Kaldi-style recipes on common audio source separation datasets are also provided. This paper describes the software architecture of Asteroid and its most important features. By showing experimental results obtained with Asteroid’s recipes, we show that our implementations are at least on par with most results reported in reference papers. The toolkit is publicly available at

 DOI: 10.21437/Interspeech.2020-1673

Cite as: Pariente, M., Cornell, S., Cosentino, J., Sivasankaran, S., Tzinis, E., Heitkaemper, J., Olvera, M., Stöter, F., Hu, M., Martín-Doñas, J.M., Ditter, D., Frank, A., Deleforge, A., Vincent, E. (2020) Asteroid: The PyTorch-Based Audio Source Separation Toolkit for Researchers. Proc. Interspeech 2020, 2637-2641, DOI: 10.21437/Interspeech.2020-1673.

  author={Manuel Pariente and Samuele Cornell and Joris Cosentino and Sunit Sivasankaran and Efthymios Tzinis and Jens Heitkaemper and Michel Olvera and Fabian-Robert Stöter and Mathieu Hu and Juan M. Martín-Doñas and David Ditter and Ariel Frank and Antoine Deleforge and Emmanuel Vincent},
  title={{Asteroid: The PyTorch-Based Audio Source Separation Toolkit for Researchers}},
  booktitle={Proc. Interspeech 2020},