Recherche

Recherche simple

Recherche avancée

Panier électronique

Votre panier ne contient aucune notice

Connexion à la base

Identification

(Identifiez-vous pour accéder aux fonctions de mise à jour. Utilisez votre login-password de courrier électronique)

Entrepôt OAI-PMH

Soumettre une requête

	Consulter la notice détaillée
	Version complète en ligne
	Version complète en ligne accessible uniquement depuis l'Ircam
	Ajouter la notice au panier
	Retirer la notice du panier

English version

(full translation not yet available)

Liste complète des articles

Consultation des notices

Vue détaillée

Vue Refer

Vue Labintel

Vue BibTeX

%0 Conference Proceedings
%A Bouvier, Damien
%A Obin, Nicolas
%A Liuni, Marco
%A Roebel, Axel
%T A Source/Filter Model with Adaptive Constraints for NMF-based Speech Separation
%D 2016
%B International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
%C Shanghai
%F Bouvier16a
%K speech separation
%K non-negative matrix factorization
%K source/filter model
%K constraints
%X This paper introduces a constrained source/filter model for semi- supervised speech separation based on non-negative matrix factorization (NMF). The objective is to inform NMF with prior knowledge about speech, providing a physically meaningful speech separation. To do so, a source/filter model (indicated as Instantaneous Mixture Model or IMM) is integrated in the NMF. Further- more, constraints are added to the IMM-NMF, in order to control the NMF behaviour during separation, and to enforce its physical meaning. In particular, a speech specific constraint - based on the source/filter coherence of speech - and a method for the automatic adaptation of constraints’ weights during separation are presented. Also, the proposed source/filter model is semi-supervised: during training, one filter basis is estimated for each phoneme of a speaker; during separation, the estimated filter bases are then used in the constrained source/filter model. An experimental evaluation for speech separation was conducted on the TIMIT speakers database mixed with various environmental background noises from the QUT- NOISE database. This evaluation showed that the use of adaptive constraints increases the performance of the source/filter model for speaker-dependent speech separation, and compares favorably to fully-supervised speech separation.
%1 6
%2 2
%U http://architexte.ircam.fr/textes/Bouvier16a/