Expectation-Maximization for Speech Source Separation using Convolutive Transfer Function - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles CAAI Transactions on Intelligent Technologies Year : 2019

Expectation-Maximization for Speech Source Separation using Convolutive Transfer Function

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
Fichier principal
Vignette du fichier
ctf_em.pdf (448.93 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01982250 , version 1 (15-01-2019)

Identifiers

Cite

Xiaofei Li, Laurent Girin, Radu Horaud. Expectation-Maximization for Speech Source Separation using Convolutive Transfer Function. CAAI Transactions on Intelligent Technologies, 2019, 4 (1), pp.47 - 53. ⟨10.1049/trit.2018.1061⟩. ⟨hal-01982250⟩
131 View
278 Download

Altmetric

Share

Gmail Facebook X LinkedIn More