A fast EM algorithm for Gaussian model-based source separation

Joachim Thiemann 1, 2 Emmanuel Vincent 3
1 PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
2 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
3 PAROLE - Analysis, perception and recognition of speech
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : We consider the FASST framework for audio source separation, which models the sources by full-rank spatial covariance matrices and multilevel nonnegative matrix factorization (NMF) spectra. The computational cost of the expectation-maximization (EM) algorithm in [1] greatly increases with the number of channels. We present alternative EM updates using discrete hidden variables which exhibit a smaller cost. We evaluate the results on mixtures of speech and real-world environmental noise taken from our DEMAND database. The proposed algorithm is several orders of magnitude faster and it provides better separation quality for two-channel mixtures in low input signal-to-noise ratio (iSNR) conditions.
Type de document :
Communication dans un congrès
EUSIPCO - 21st European Signal Processing Conference - 2013, Sep 2013, Marrakech, Morocco. 2013
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00840366
Contributeur : Emmanuel Vincent <>
Soumis le : mardi 2 juillet 2013 - 12:38:04
Dernière modification le : vendredi 16 novembre 2018 - 01:32:16
Document(s) archivé(s) le : mercredi 5 avril 2017 - 06:03:21

Fichier

thiemann_EUSIPCO13.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00840366, version 1

Citation

Joachim Thiemann, Emmanuel Vincent. A fast EM algorithm for Gaussian model-based source separation. EUSIPCO - 21st European Signal Processing Conference - 2013, Sep 2013, Marrakech, Morocco. 2013. 〈hal-00840366〉

Partager

Métriques

Consultations de la notice

815

Téléchargements de fichiers

443