Underdetermined Reverberant Blind Source Separation: Sparse Approaches for Multiplicative and Convolutive Narrowband Approximation

Fangchen Feng 1 Matthieu Kowalski 2
1 APC - UMR 7164 - AstroParticule et Cosmologie
2 Division Signaux - L2S
L2S - Laboratoire des signaux et systèmes : 1289
Abstract : —We consider the problem of blind source separation for underdetermined convolutive mixtures. Based on the multiplicative narrowband approximation in the time-frequency domain with the help of Short-Time-Fourier-Transform (STFT) and the sparse representation of the source signals, we formulate the separation problem into an optimization framework. This framework is then generalized based on the recently investigated convolutive narrowband approximation and the statistics of the room impulse response. Algorithms with convergence proof are then employed to solve the proposed optimization problems. The evaluation of the proposed frameworks and algorithms for synthesized and live recorded mixtures are illustrated. The proposed approaches are also tested for mixtures with input noise. Numerical evaluations show the advantages of the proposed methods.
Keywords : Blind source separation BSS Sparse regularization Room impulse responses Optimization Algorithms
Type de document :
Pré-publication, Document de travail
2018
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger
https://hal.archives-ouvertes.fr/hal-01760968
Contributeur : Fangchen Feng <>
Soumis le : vendredi 6 avril 2018 - 22:05:50
Dernière modification le : jeudi 15 novembre 2018 - 20:27:15

Fichier

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

Identifiants

  • HAL Id : hal-01760968, version 1

Collections

SUP_LSS | SUP_SIGNAUX | IRFU-APC | L2S | CEA | USPC | CENTRALESUPELEC | DSM-IRFU | PSL | IN2P3 | APC | OBSPM | UNIV-PARIS-SACLAY | CEA-DRF

Citation

Fangchen Feng, Matthieu Kowalski. Underdetermined Reverberant Blind Source Separation: Sparse Approaches for Multiplicative and Convolutive Narrowband Approximation. 2018. 〈hal-01760968〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

304

Téléchargements de fichiers

65

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD