Skip to Main content Skip to Navigation
Conference papers

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 neu-ral 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.
Complete list of metadata

Cited literature [46 references]  Display  Hide  Download

https://hal.inria.fr/hal-02962964
Contributor : Manuel Pariente Connect in order to contact the contributor
Submitted on : Friday, October 9, 2020 - 3:55:09 PM
Last modification on : Saturday, October 16, 2021 - 11:26:10 AM
Long-term archiving on: : Sunday, January 10, 2021 - 6:52:25 PM

File

old_main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02962964, version 1

Citation

Manuel Pariente, Samuele Cornell, Joris Cosentino, Sunit Sivasankaran, Efthymios Tzinis, et al.. Asteroid: the PyTorch-based audio source separation toolkit for researchers. Interspeech 2020, Oct 2020, Shanghai, China. ⟨hal-02962964⟩

Share

Metrics

Record views

407

Files downloads

522