Weighted nonnegative tensor factorization: on monotonicity of multiplicative update rules and application to user-guided audio source separation

Abstract : This report focuses on so-called weighted variants of nonnnegative matrix factorization (NMF) and more generally nonnnegative tensor factorization (NTF) approximations. First, we consider multiplicative update (MU) rules to optimize these approximations, and we prove that some results on monotonicity of MU rules for NMF generalize without restrictions to both the NTF and the WNTF cases. Second, we propose new weighting strategies for an existing NTF-based user-guided audio source separation method. Experimental evaluation shows that these weightings lead to better source separation than the same model without using the weights. The best configuration of the proposed method was entered into the fourth community-based Signal Separation Evaluation Campaign (SiSEC 2013).
Liste complète des métadonnées

Littérature citée [28 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00878685
Contributeur : Alexey Ozerov <>
Soumis le : vendredi 21 mars 2014 - 14:11:42
Dernière modification le : vendredi 16 septembre 2016 - 15:18:10
Document(s) archivé(s) le : samedi 21 juin 2014 - 11:45:31

Fichier

Ozerov_et_al_TechRepTEC_2013.p...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00878685, version 2

Collections

Citation

Alexey Ozerov, Ngoc Duong, Louis Chevallier. Weighted nonnegative tensor factorization: on monotonicity of multiplicative update rules and application to user-guided audio source separation. [Research Report] 2013, pp.10. 〈hal-00878685v2〉

Partager

Métriques

Consultations de la notice

158

Téléchargements de fichiers

156