Adaptation of Bayesian models for single channel source separation and its application to voice / music separation in popular songs - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Audio, Speech and Language Processing Year : 2007

Adaptation of Bayesian models for single channel source separation and its application to voice / music separation in popular songs

Abstract

Probabilistic approaches can offer satisfactory solutions to source separation with a single channel, provided that the models of the sources match accurately the statistical properties of the mixed signals. However, it is not always possible to train such models. To overcome this problem, we propose to resort to an adaptation scheme for adjusting the source models with respect to the actual properties of the signals observed in the mix. In this paper, we introduce a general formalism for source model adaptation which is expressed in the framework of Bayesian models. Particular cases of the proposed approach are then investigated experimentally on the problem of separating voice from music in popular songs. The obtained results show that an adaptation scheme can improve consistently and significantly the separation performance in comparison with nonadapted models.
Fichier principal
Vignette du fichier
2007_IEEE_TASLP_OzerovEtAl_SingleChannelSourceSeparation.pdf (904.84 Ko) Télécharger le fichier
Origin : Explicit agreement for this submission
Loading...

Dates and versions

inria-00544774 , version 1 (08-02-2011)

Identifiers

Cite

Alexey Ozerov, Pierrick Philippe, Frédéric Bimbot, Rémi Gribonval. Adaptation of Bayesian models for single channel source separation and its application to voice / music separation in popular songs. IEEE Transactions on Audio, Speech and Language Processing, 2007, 15 (5), pp.1564--1578. ⟨10.1109/TASL.2007.899291⟩. ⟨inria-00544774⟩
198 View
1050 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More