Two Multimodal Approaches for Single Microphone Source Separation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Two Multimodal Approaches for Single Microphone Source Separation

Résumé

—In this paper, the problem of single microphone source separation via Nonnegative Matrix Factorization (NMF) by exploiting video information is addressed. Respective audio and video modalities coming from a single human speech usually have similar time changes. It means that changes in one of them usually corresponds to changes in the other one. So it is expected that activation coefficient matrices of their NMF decomposition are similar. Based on this similarity, in this paper the activation coefficient matrix of the video modality is used as an initialization for audio source separation via NMF. In addition, the mentioned similarity is used for post-processing and for clustering the rows of the activation coefficient matrix which were resulted from randomly initialized NMF. Simulation results confirm the effectiveness of the proposed multimodal approaches in single microphone source separation.
Fichier principal
Vignette du fichier
1570251892.pdf (189.02 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01400542 , version 1 (22-11-2016)

Identifiants

  • HAL Id : hal-01400542 , version 1

Citer

Farnaz Sedighin, Massoud Babaie-Zadeh, Bertrand Rivet, Christian Jutten. Two Multimodal Approaches for Single Microphone Source Separation. EUSIPCO 2016 - 24th European Signal Processing Conference, Aug 2016, Budapest, Hungary. pp.110-114. ⟨hal-01400542⟩
298 Consultations
328 Téléchargements

Partager

Gmail Facebook X LinkedIn More