Content-adaptive speech enhancement by a sparsely-activated dictionary plus low rank decomposition

Abstract : One powerful approach to speech enhancement employs strong models for both speech and noise, decomposing a mixture into the most likely combination. But if the noise encountered differs significantly from the system's assumptions, performance will suffer. In previous work, we proposed a speech enhancement model that decomposes the spectrogram into sparse activation of a dictionary of target speech templates, and a low-rank background model. This makes few assumptions about the noise, and gave appealing results on small excerpts of noisy speech. However, when processing whole conversations, the foreground speech may vary in its complexity and may be unevenly distributed throughout the recording, resulting in inaccurate decompositions for some segments. In this paper, we explore an adaptive formulation of our previous model that incorporates separate side information to guide the decomposition, making it able to better process entire conversations that may exhibit large variations in the speech content.
Type de document :
Communication dans un congrès
IEEE Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), May 2014, Nancy, France. pp.16-20, 2014, 〈10.1109/HSCMA.2014.6843242〉
Liste complète des métadonnées

Littérature citée [30 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01104904
Contributeur : I Papadopoulos <>
Soumis le : lundi 19 janvier 2015 - 14:15:34
Dernière modification le : vendredi 27 juillet 2018 - 19:09:23
Document(s) archivé(s) le : vendredi 11 septembre 2015 - 07:10:22

Fichier

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

Identifiants

Collections

Citation

Zhuo Chen, Hélène Papadopoulos, Daniel P.W. Ellis. Content-adaptive speech enhancement by a sparsely-activated dictionary plus low rank decomposition. IEEE Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), May 2014, Nancy, France. pp.16-20, 2014, 〈10.1109/HSCMA.2014.6843242〉. 〈hal-01104904〉

Partager

Métriques

Consultations de la notice

234

Téléchargements de fichiers

327