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

doi:10.21437/Interspeech.2020-1673

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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

116 Scopus citations

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.

Original language	English
Title of host publication	Interspeech 2020
Publisher	International Speech Communication Association
Pages	2637-2641
Number of pages	5
ISBN (Print)	9781713820697
DOIs	https://doi.org/10.21437/Interspeech.2020-1673
State	Published - 2020
Externally published	Yes
Event	21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 - Shanghai, China Duration: 25 Oct 2020 → 29 Oct 2020

Publication series

Name	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume	2020-October
ISSN (Print)	2308-457X
ISSN (Electronic)	1990-9772

Conference

Conference	21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020
Country/Territory	China
City	Shanghai
Period	25/10/20 → 29/10/20

Bibliographical note

Publisher Copyright:
© 2020 International Speech Communication Association. All rights reserved.

Keywords

End-to-end
Open-source software
Source separation
Speech enhancement

Access to Document

10.21437/Interspeech.2020-1673

Cite this

Pariente, M., Cornell, S., Cosentino, J., Sivasankaran, S., Tzinis, E., Heitkaemper, J., Olvera, M., Stöter, F. R., 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. In Interspeech 2020 (pp. 2637-2641). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 2020-October). International Speech Communication Association. https://doi.org/10.21437/Interspeech.2020-1673

@inproceedings{f3cd7949d9b84ff0b59bd31bf0faeed7,

title = "Asteroid: The PyTorch-based audio source separation toolkit for researchers",

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.",

keywords = "End-to-end, Open-source software, Source separation, Speech enhancement",

author = "Manuel Pariente and Samuele Cornell and Joris Cosentino and Sunit Sivasankaran and Efthymios Tzinis and Jens Heitkaemper and Michel Olvera and St{\"o}ter, \{Fabian Robert\} and Mathieu Hu and Mart{\'i}n-Do{\~n}as, \{Juan M.\} and David Ditter and Ariel Frank and Antoine Deleforge and Emmanuel Vincent",

note = "Publisher Copyright: {\textcopyright} 2020 International Speech Communication Association. All rights reserved.; 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 ; Conference date: 25-10-2020 Through 29-10-2020",

year = "2020",

doi = "10.21437/Interspeech.2020-1673",

language = "אנגלית",

isbn = "9781713820697",

series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

publisher = "International Speech Communication Association",

pages = "2637--2641",

booktitle = "Interspeech 2020",

}

Pariente, M, Cornell, S, Cosentino, J, Sivasankaran, S, Tzinis, E, Heitkaemper, J, Olvera, M, Stöter, FR, Hu, M, Martín-Doñas, JM, Ditter, D, Frank, A, Deleforge, A & Vincent, E 2020, Asteroid: The PyTorch-based audio source separation toolkit for researchers. in Interspeech 2020. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2020-October, International Speech Communication Association, pp. 2637-2641, 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020, Shanghai, China, 25/10/20. https://doi.org/10.21437/Interspeech.2020-1673

Asteroid: The PyTorch-based audio source separation toolkit for researchers. / Pariente, Manuel; Cornell, Samuele; Cosentino, Joris et al.
Interspeech 2020. International Speech Communication Association, 2020. p. 2637-2641 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 2020-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Asteroid

T2 - 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020

AU - Pariente, Manuel

AU - Cornell, Samuele

AU - Cosentino, Joris

AU - Sivasankaran, Sunit

AU - Tzinis, Efthymios

AU - Heitkaemper, Jens

AU - Olvera, Michel

AU - Stöter, Fabian Robert

AU - Hu, Mathieu

AU - Martín-Doñas, Juan M.

AU - Ditter, David

AU - Frank, Ariel

AU - Deleforge, Antoine

AU - Vincent, Emmanuel

PY - 2020

Y1 - 2020

N2 - 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.

AB - 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.

KW - End-to-end

KW - Open-source software

KW - Source separation

KW - Speech enhancement

UR - https://www.scopus.com/pages/publications/85097970123

U2 - 10.21437/Interspeech.2020-1673

DO - 10.21437/Interspeech.2020-1673

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85097970123

SN - 9781713820697

T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SP - 2637

EP - 2641

BT - Interspeech 2020

PB - International Speech Communication Association

Y2 - 25 October 2020 through 29 October 2020

ER -

Pariente M, Cornell S, Cosentino J, Sivasankaran S, Tzinis E, Heitkaemper J et al. Asteroid: The PyTorch-based audio source separation toolkit for researchers. In Interspeech 2020. International Speech Communication Association. 2020. p. 2637-2641. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). doi: 10.21437/Interspeech.2020-1673

Asteroid: The PyTorch-based audio source separation toolkit for researchers

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this