Flow-Based Fast Multichannel Nonnegative Matrix Factorization for Blind Source Separation - Laboratoire Traitement et Communication de l'Information Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Flow-Based Fast Multichannel Nonnegative Matrix Factorization for Blind Source Separation

Résumé

This paper describes a blind source separation method for multichannel audio signals, called NF-FastMNMF, based on the integration of the normalizing flow (NF) into the multichannel nonnegative matrix factorization with jointly-diagonalizable spatial covariance matrices, a.k.a. FastMNMF. Whereas the NF of flow-based independent vector analysis, called NF-IVA, acts as the demixing matrices to transform an M-channel mixture into M independent sources, the NF of NF-FastMNMF acts as the diagonalization matrices to transform an Mchannel mixture into a spatially-independent M-channel mixture represented as a weighted sum of N source images. This diagonalization enables the NF, which has been used only for determined separation because of its bijective nature, to be applicable to non-determined separation. NF-FastMNMF has time-varying diagonalization matrices that are potentially better at handling dynamical data variation than the time-invariant ones in FastMNMF. To have an NF with richer expression capability, the dimension-wise scalings using diagonal matrices originally used in NF-IVA are replaced with linear transformations using upper triangular matrices; in both cases, the diagonal and upper triangular matrices are estimated by neural networks. The evaluation shows that NF-FastMNMF performs well for both determined and non-determined separations of multiple speech utterances by stationary or non-stationary speakers from a noisy reverberant mixture.
Fichier principal
Vignette du fichier
_ICASSP_22__NF_FastMNMF.pdf (266.68 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03637425 , version 1 (11-04-2022)

Identifiants

  • HAL Id : hal-03637425 , version 1

Citer

Aditya Arie Nugraha, Kouhei Sekiguchi, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii. Flow-Based Fast Multichannel Nonnegative Matrix Factorization for Blind Source Separation. 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022), May 2022, Singapore, Singapore. ⟨hal-03637425⟩
246 Consultations
251 Téléchargements

Partager

Gmail Facebook X LinkedIn More