Speech enhancement based on nonnegative matrix factorization with mixed group sparsity constraint

Abstract : This paper addresses a challenging single-channel speech enhancement problem in real-world environment where speech signal is corrupted by high level background noise. While most state-of-the-art algorithms tries to estimate noise spectral power and filter it from the observed one to obtain enhanced speech, the paper discloses another approach inspired from audio source separation technique. In the considered method, generic spectral characteristics of speech and noise are first learned from various training signals by non-negative matrix factorization (NMF). They are then used to guide the similar factorization of the observed power spectrogram into speech part and noise part. Additionally, we propose to combine two existing group sparsity-inducing penalties in the optimization process and adapt the corresponding algorithm for parameter estimation based on mul-tiplicative update (MU) rule. Experiment results over different settings confirm the effectiveness of the proposed approach .
Type de document :
Communication dans un congrès
6th ACM International Symposium on Information and Communication Technology, Dec 2015, Hanoi, Vietnam. 〈10.1145/2833258.2833276〉
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01288291
Contributeur : Ngoc Duong <>
Soumis le : mardi 15 mars 2016 - 11:06:10
Dernière modification le : jeudi 11 janvier 2018 - 06:23:16
Document(s) archivé(s) le : jeudi 16 juin 2016 - 10:34:33

Fichier

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

Identifiants

Collections

Citation

Hien-Thanh Duong, Quoc-Cuong Nguyen, Cong-Phuong Nguyen, Thanh-Huan Tran, Ngoc Q. K. Duong. Speech enhancement based on nonnegative matrix factorization with mixed group sparsity constraint. 6th ACM International Symposium on Information and Communication Technology, Dec 2015, Hanoi, Vietnam. 〈10.1145/2833258.2833276〉. 〈hal-01288291〉

Partager

Métriques

Consultations de la notice

74

Téléchargements de fichiers

150