Published October 25, 2020 | Version v1
Conference paper

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

Contributors

Others:

Description

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.

Abstract

Fully Virtual Conference

Abstract

International audience

Additional details

Identifiers

URL
https://inria.hal.science/hal-02962964
URN
urn:oai:HAL:hal-02962964v1

Origin repository

Origin repository
UNICA