Asteroid: the PyTorch-based audio source separation toolkit for researchers
Manuel Pariente
Samuele Cornell
Joris Cosentino
S. Sivasankaran
Efthymios Tzinis
Jens Heitkaemper
Michel Olvera
Fabian-Robert Stöter
Mathieu Hu
Juan M. Martín-Donas
David Ditter
Ariel Frank
Antoine Deleforge
Emmanuel Vincent

Abstract
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 https://github.com/mpariente/asteroid .
View on arXivComments on this paper