Comment évaluer les algorithmes de séparation de sources audio ?

Abstract : In this article, we describe a few applications of audio source separation and we propose some ideas towards the construction of an agreed-upon evaluation framework for audio source separation algorithms. Our work is composed of three steps : identifying the typical tasks to be addressed by the algorithms, designing numerical performance criteria, and collecting relevant datasets.
Liste complète des métadonnées

Cited literature [11 references]  Display  Hide  Download

https://hal.inria.fr/inria-00544248
Contributor : Emmanuel Vincent <>
Submitted on : Tuesday, December 7, 2010 - 3:28:43 PM
Last modification on : Thursday, March 21, 2019 - 2:20:03 PM
Document(s) archivé(s) le : Tuesday, March 8, 2011 - 4:36:53 AM

File

vincent_GRETSI03.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : inria-00544248, version 1

Citation

Emmanuel Vincent, Cédric Févotte, Rémi Gribonval, Laurent Benaroya, Xavier Rodet, et al.. Comment évaluer les algorithmes de séparation de sources audio ?. 19e colloque GRETSI sur le traitement du signal et des images, Sep 2003, Paris, France. pp.27--30. ⟨inria-00544248⟩

Share

Metrics

Record views

603

Files downloads

642