Published July 2, 2018 | Version v1
Conference paper Metadata-only

Multichannel Audio Modeling with Elliptically Stable Tensor Decomposition

Creators

Contributors

Others:

Description

This paper introduces a new method for multichannel speech enhancement based on a versatile modeling of the residual noise spec-trogram. Such a model has already been presented before in the single channel case where the noise component is assumed to follow an alpha-stable distribution for each time-frequency bin, whereas the speech spec-trogram, supposed to be more regular, is modeled as Gaussian. In this paper, we describe a multichannel extension of this model, as well as a Monte Carlo Expectation-Maximisation algorithm for parameter estimation. In particular, a multichannel extension of the Itakura-Saito nonnegative matrix factorization is exploited to estimate the spectral parameters for speech, and a Metropolis-Hastings algorithm is proposed to estimate the noise contribution. We evaluate the proposed method in a challenging multichannel denoising application and compare it to other state-of-the-art algorithms.

Abstract

International audience

Additional details

Identifiers

URL
https://hal-lirmm.ccsd.cnrs.fr/lirmm-01766795
URN
urn:oai:HAL:lirmm-01766795v1

Origin repository

Origin repository
UNICA