Blind criterion and oracle bound for instantaneous audio source separation using adaptive time-frequency representations

Emmanuel Vincent 1 Rémi Gribonval 1
1 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : The separation of multichannel audio mixtures is often addressed by the masking approach, which consists of representing the mixture signal in the time-frequency domain and associating each time-frequency bin with a small number of active sources. Adaptive time-frequency representations can increase the disjointness of the sources compared to fixed representations. However their use has not been conclusive so far. In this paper, we propose a new criterion for the blind estimation of an adapted representation of an instantaneous mixture and explain how to compute the oracle representation leading to the best possible performance given reference source signals. Experimental results suggest that a small separation performance improvement can indeed be achieved using adaptive representations, but that complementary approaches must be investigated to obtain larger improvements.
Document type :
Conference papers
2007 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), Oct 2007, New Paltz, United States. pp.110--113, 2007
Liste complète des métadonnées

https://hal.inria.fr/inria-00544207
Contributor : Emmanuel Vincent <>
Submitted on : Tuesday, December 7, 2010 - 2:57:31 PM
Last modification on : Friday, January 13, 2017 - 2:16:43 PM
Document(s) archivé(s) le : Tuesday, March 8, 2011 - 2:48:06 AM

File

vincent_WASPAA07.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : inria-00544207, version 1

Collections

Citation

Emmanuel Vincent, Rémi Gribonval. Blind criterion and oracle bound for instantaneous audio source separation using adaptive time-frequency representations. 2007 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), Oct 2007, New Paltz, United States. pp.110--113, 2007. <inria-00544207>

Share

Metrics

Record views

242

Document downloads

158