SINGLE-CHANNEL SPEAKER-DEPENDENT SPEECH ENHANCEMENT EXPLOITING GENERIC NOISE MODEL LEARNED BY NON-NEGATIVE MATRIX FACTORIZATION

Abstract : This paper considers the single-channel speech separation problem given a noisy observation recorded by a microphone. More precisely, we focus on the speaker-dependent approach where spectral characteristic of target speech is learned in advance from a clean example. In training process, we propose to learn a generic spectral model for noise source by collecting various types of environmental noise via the established non-negative matrix factorization framework. In speech enhancement process, we propose to combine two existing group sparsity-inducing penalties in the optimization function and derive the corresponding algorithm for parameter estimation based on multiplicative update (MU) rule. Experiment result over mixtures containing different real-world noises confirms the effectiveness of our approach.
Type de document :
Communication dans un congrès
IEEE International Conference on Electronics, Information and Communication, Jan 2016, Da Nang, Vietnam
Liste complète des métadonnées

Littérature citée [7 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01288277
Contributeur : Ngoc Duong <>
Soumis le : mardi 15 mars 2016 - 11:07:10
Dernière modification le : lundi 8 octobre 2018 - 21:06:02
Document(s) archivé(s) le : jeudi 16 juin 2016 - 10:39:47

Fichier

iceic2016_Edit2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01288277, version 1

Collections

Citation

Hien-Thanh Duong, Quoc-Cuong Nguyen, Cong-Phuong Nguyen, Ngoc Q. K. Duong. SINGLE-CHANNEL SPEAKER-DEPENDENT SPEECH ENHANCEMENT EXPLOITING GENERIC NOISE MODEL LEARNED BY NON-NEGATIVE MATRIX FACTORIZATION. IEEE International Conference on Electronics, Information and Communication, Jan 2016, Da Nang, Vietnam. 〈hal-01288277〉

Partager

Métriques

Consultations de la notice

59

Téléchargements de fichiers

92