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

M. Pariente, S. Cornell, J. Cosentino, S. Sivasankaran, E. Tzinis, J. Heitkaemper, M. Olvera, F.-R. Stöter, M. Hu, J.M. Martín-Doñas, D. Ditter, A. Frank, A. Deleforge, E. Vincent, in: Interspeech 2020, 2020.

Download
No fulltext has been uploaded.
Conference Paper | Published | English
Author
; ; ; ; ; ; ; ; ; ; ;
All
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 github.com/mpariente/asteroid.
Publishing Year
Proceedings Title
Interspeech 2020
LibreCat-ID

Cite this

Pariente M, Cornell S, Cosentino J, et al. Asteroid: The PyTorch-Based Audio Source Separation Toolkit for Researchers. In: Interspeech 2020. ; 2020. doi:10.21437/interspeech.2020-1673
Pariente, M., Cornell, S., Cosentino, J., Sivasankaran, S., Tzinis, E., Heitkaemper, J., … Vincent, E. (2020). Asteroid: The PyTorch-Based Audio Source Separation Toolkit for Researchers. In Interspeech 2020. https://doi.org/10.21437/interspeech.2020-1673
@inproceedings{Pariente_Cornell_Cosentino_Sivasankaran_Tzinis_Heitkaemper_Olvera_Stöter_Hu_Martín-Doñas_et al._2020, title={Asteroid: The PyTorch-Based Audio Source Separation Toolkit for Researchers}, DOI={10.21437/interspeech.2020-1673}, booktitle={Interspeech 2020}, author={Pariente, Manuel and Cornell, Samuele and Cosentino, Joris and Sivasankaran, Sunit and Tzinis, Efthymios and Heitkaemper, Jens and Olvera, Michel and Stöter, Fabian-Robert and Hu, Mathieu and Martín-Doñas, Juan M. and et al.}, year={2020} }
Pariente, Manuel, Samuele Cornell, Joris Cosentino, Sunit Sivasankaran, Efthymios Tzinis, Jens Heitkaemper, Michel Olvera, et al. “Asteroid: The PyTorch-Based Audio Source Separation Toolkit for Researchers.” In Interspeech 2020, 2020. https://doi.org/10.21437/interspeech.2020-1673.
M. Pariente et al., “Asteroid: The PyTorch-Based Audio Source Separation Toolkit for Researchers,” in Interspeech 2020, 2020.
Pariente, Manuel, et al. “Asteroid: The PyTorch-Based Audio Source Separation Toolkit for Researchers.” Interspeech 2020, 2020, doi:10.21437/interspeech.2020-1673.

Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar