Blind audio source separation using two expectation-maximization algorithms

Aviad Eisenberg, Boaz Schwartz, Sharon Gannot

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

The problem of multi-microphone blind audio source separation in noisy environment is addressed. The estimation of the acoustic signals and the associated parameters is carried out using the expectation-maximization algorithm. Two separation algorithms are developed using either deterministic representation or stochastic Gaussian distribution for modelling the speech signals. Under the deterministic model, the speech sources are estimated in the M-step by applying in parallel multiple minimum variance distortionless response (MVDR) beamformers, while under the stochastic model, the speech signals are estimated in the E-step by applying in parallel multiple multichannel Wiener filters (MCWF). In the simulation study, we generated a large dataset of microphone signals, by convolving speech signals, with overlapping activity patterns, by measured acoustic impulse responses. It is shown that the proposed methods outperform a baseline method in terms of speech quality and intelligibility.

Original languageEnglish
Title of host publicationProceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020
PublisherIEEE Computer Society
ISBN (Electronic)9781728166629
DOIs
StatePublished - Sep 2020
Event30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020 - Virtual, Espoo, Finland
Duration: 21 Sep 202024 Sep 2020

Publication series

NameIEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume2020-September
ISSN (Print)2161-0363
ISSN (Electronic)2161-0371

Conference

Conference30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020
Country/TerritoryFinland
CityVirtual, Espoo
Period21/09/2024/09/20

Bibliographical note

Funding Information:
This project has received funding from the European Union’s Horizon 2020 Research and Innovation Programme, Grant Agreement No. 871245.

Publisher Copyright:
© 2020 IEEE.

Keywords

  • Blind audio source separation
  • Expectation-maximization algorithm
  • MVDR and multichannel Wiener filter beamforming

Fingerprint

Dive into the research topics of 'Blind audio source separation using two expectation-maximization algorithms'. Together they form a unique fingerprint.

Cite this