Published October 25, 2020
| Version v1
Conference paper
Asteroid: the PyTorch-based audio source separation toolkit for researchers
Contributors
Others:
- Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH) ; Centre Inria de l'Université de Lorraine ; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD) ; Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA) ; Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA) ; Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)
- Polytechnic University of Marche / Università Politecnica delle Marche (UNIVPM)
- Department of Electrical and Computer Engineering [Urbana] (University of Illinois) ; University of Illinois at Urbana-Champaign [Urbana] (UIUC) ; University of Illinois System-University of Illinois System
- University of Paderborn
- Scientific Data Management (ZENITH) ; Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM) ; Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Centre Inria d'Université Côte d'Azur (CRISAM) ; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
- Universidad de Granada = University of Granada (UGR)
- Universität Hamburg = University of Hamburg (UHH)
- Technion - Israel Institute of Technology [Haifa]
- Grid'5000
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 ConferenceAbstract
International audienceAdditional details
Identifiers
- URL
- https://inria.hal.science/hal-02962964
- URN
- urn:oai:HAL:hal-02962964v1
Origin repository
- Origin repository
- UNICA