Expectation-Maximization for Speech Source Separation using Convolutive Transfer Function

Xiaofei Li 1 Laurent Girin 2 Radu Horaud 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 GIPSA-CRISSP - CRISSP
GIPSA-DPC - Département Parole et Cognition
Abstract : This paper addresses the problem of under-determinded speech source separation from multichannel microphone singals, i.e. the convolutive mixtures of multiple sources. The time-domain signals are first transformed to the short-time Fourier transform (STFT) domain. To represent the room filters in the STFT domain, instead of the widely-used narrowband assumption, we propose to use a more accurate model, i.e. the convolutive transfer function (CTF). At each frequency band, the CTF coefficients of the mixing filters and the STFT coefficients of the sources are jointly estimated by maximizing the likelihood of the microphone signals, which is resolved by an Expectation-Maximization (EM) algorithm. Experiments show that the proposed method provides very satisfactory performance under highly reverberant environments
Type de document :
Article dans une revue
CAAI Transactions on Intelligent Technologies, Elsevier B.V., 2019, pp.1-8. 〈10.1049/trit.2018.1061〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01982250
Contributeur : Team Perception <>
Soumis le : mardi 15 janvier 2019 - 15:10:49
Dernière modification le : jeudi 7 février 2019 - 16:24:51

Fichier

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

Identifiants

Citation

Xiaofei Li, Laurent Girin, Radu Horaud. Expectation-Maximization for Speech Source Separation using Convolutive Transfer Function. CAAI Transactions on Intelligent Technologies, Elsevier B.V., 2019, pp.1-8. 〈10.1049/trit.2018.1061〉. 〈hal-01982250〉

Partager

Métriques

Consultations de la notice

61

Téléchargements de fichiers

47