Under-Determined Reverberant Audio Source Separation Using Local Observed Covariance and Auditory-Motivated Time-Frequency Representation

Ngoc Duong 1 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 : We consider the local Gaussian modeling framework for under-determined convolutive audio source separation, where the spatial image of each source is modeled as a zero-mean Gaussian variable with full-rank time- and frequency- dependent covariance. We investigate two methods to improve the accuracy of parameter estimation, based on the use of local observed covariance and auditory-motivated time-frequency representation. We derive an iterative expectation-maximization (EM) algorithm with a suitable initialization scheme. Experimental results over stereo synthetic reverberant mixtures of speech show the effectiveness of the proposed methods.
Type de document :
Communication dans un congrès
Vincent Vigneron and Vicente Zarzoso and Eric Moreau and Rémi Gribonval and Emmanuel Vincent. Latent Variable Analysis and Signal Separation, 9th International Conference on, Sep 2010, Saint-Malo, France. Springer, 6365, pp.73--80, 2010, Lecture Notes on Computer Science. 〈10.1007/978-3-642-15995-4_10〉
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00541868
Contributeur : Rémi Gribonval <>
Soumis le : samedi 5 février 2011 - 13:00:11
Dernière modification le : mercredi 11 avril 2018 - 01:56:49
Document(s) archivé(s) le : vendredi 6 mai 2011 - 02:25:49

Fichier

2010_LVA_DuongEtAl.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Ngoc Duong, Emmanuel Vincent, Rémi Gribonval. Under-Determined Reverberant Audio Source Separation Using Local Observed Covariance and Auditory-Motivated Time-Frequency Representation. Vincent Vigneron and Vicente Zarzoso and Eric Moreau and Rémi Gribonval and Emmanuel Vincent. Latent Variable Analysis and Signal Separation, 9th International Conference on, Sep 2010, Saint-Malo, France. Springer, 6365, pp.73--80, 2010, Lecture Notes on Computer Science. 〈10.1007/978-3-642-15995-4_10〉. 〈inria-00541868〉

Partager

Métriques

Consultations de la notice

587

Téléchargements de fichiers

215