Underdetermined instantaneous audio source separation via local Gaussian modeling

Emmanuel Vincent 1 Simon Arberet 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 : Underdetermined source separation is often carried out by modeling time-frequency source coefficients via a fixed sparse prior. This approach fails when the number of active sources in one time-frequency bin is larger than the number of channels or when active sources lie on both sides of an inactive source. In this article, we partially address these issues by modeling time-frequency source coefficients via Gaussian priors with free variances. We study the resulting maximum likelihood criterion and derive a fast non-iterative optimization algorithm that finds the global minimum. We show that this algorithm outperforms state-of-the- art approaches over stereo instantaneous speech mixtures.
Type de document :
Communication dans un congrès
8th Int. Conf. on Independent Component Analysis and Signal Separation (ICA), Mar 2009, Paraty, Brazil. Springer-Verlag Berlin Heidelberg 2009, 5441/2009, pp 775-782, 2009, 〈10.1007/978-3-642-00599-2_97〉
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00482223
Contributeur : Emmanuel Vincent <>
Soumis le : lundi 10 mai 2010 - 09:18:18
Dernière modification le : jeudi 21 mars 2019 - 14:20:03
Document(s) archivé(s) le : jeudi 16 septembre 2010 - 13:48:32

Fichier

2009_ICA_VincentArberetGribonv...
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Emmanuel Vincent, Simon Arberet, Rémi Gribonval. Underdetermined instantaneous audio source separation via local Gaussian modeling. 8th Int. Conf. on Independent Component Analysis and Signal Separation (ICA), Mar 2009, Paraty, Brazil. Springer-Verlag Berlin Heidelberg 2009, 5441/2009, pp 775-782, 2009, 〈10.1007/978-3-642-00599-2_97〉. 〈hal-00482223〉

Partager

Métriques

Consultations de la notice

671

Téléchargements de fichiers

269