Online blind audio source separation using recursive expectation-maximization

Aviad Eisenberg; Boaz Schwartz; Sharon Gannot

doi:10.21437/Interspeech.2021-662

Online blind audio source separation using recursive expectation-maximization

Aviad Eisenberg, Boaz Schwartz, Sharon Gannot

Bar-Ilan University - The Alexander Kofkin Faculty of Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

The challenging problem of online multi-microphone blind audio source separation (BASS) in noisy environment is addressed in this paper. We present a sequential, non-iterative, algorithm based on the recursive EM (REM) framework. In the proposed algorithm, the compete-data, which constitutes the separated sources and residual noise, is estimated in the E-step by applying a multichannel Wiener filter (MCWF); and the corresponding parameters, comprised of acoustic transfer functions (ATFs) relating the sources and the microphones and power spectral densities (PSDs) of the desired sources, are sequentially estimated in the M-step. The separated speech signals are further enhanced using matched-filter beamformers. The performance of the algorithm is demonstrated in terms of the separation capabilities, the resulting speech intelligibility and the ability to track the direction of arrival (DOA) of the moving sources.

Original language	English
Title of host publication	22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
Publisher	International Speech Communication Association
Pages	2328-2332
Number of pages	5
ISBN (Electronic)	9781713836902
DOIs	https://doi.org/10.21437/Interspeech.2021-662
State	Published - 2021
Event	22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021 - Brno, Czech Republic Duration: 30 Aug 2021 → 3 Sep 2021

Publication series

Name	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume	3
ISSN (Print)	2308-457X
ISSN (Electronic)	1990-9772

Conference

Conference	22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
Country/Territory	Czech Republic
City	Brno
Period	30/08/21 → 3/09/21

Bibliographical note

Funding Information:
The project received funding from the EU Horizon 2020 Research and Innovation Programme, Grant Agreement #871245.

Publisher Copyright:
Copyright © 2021 ISCA.

Keywords

Multichannel Wiener filter beamforming
Recursive expectation maximization
blind audio source separation

Access to Document

10.21437/Interspeech.2021-662

Cite this

Eisenberg, A., Schwartz, B., & Gannot, S. (2021). Online blind audio source separation using recursive expectation-maximization. In 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021 (pp. 2328-2332). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 3). International Speech Communication Association. https://doi.org/10.21437/Interspeech.2021-662

Eisenberg, Aviad ; Schwartz, Boaz ; Gannot, Sharon. / Online blind audio source separation using recursive expectation-maximization. 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021. International Speech Communication Association, 2021. pp. 2328-2332 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

@inproceedings{71174428d9c84bea8928930e4a8563dd,

title = "Online blind audio source separation using recursive expectation-maximization",

abstract = "The challenging problem of online multi-microphone blind audio source separation (BASS) in noisy environment is addressed in this paper. We present a sequential, non-iterative, algorithm based on the recursive EM (REM) framework. In the proposed algorithm, the compete-data, which constitutes the separated sources and residual noise, is estimated in the E-step by applying a multichannel Wiener filter (MCWF); and the corresponding parameters, comprised of acoustic transfer functions (ATFs) relating the sources and the microphones and power spectral densities (PSDs) of the desired sources, are sequentially estimated in the M-step. The separated speech signals are further enhanced using matched-filter beamformers. The performance of the algorithm is demonstrated in terms of the separation capabilities, the resulting speech intelligibility and the ability to track the direction of arrival (DOA) of the moving sources.",

keywords = "Multichannel Wiener filter beamforming, Recursive expectation maximization, blind audio source separation",

author = "Aviad Eisenberg and Boaz Schwartz and Sharon Gannot",

note = "Publisher Copyright: Copyright {\textcopyright} 2021 ISCA.; 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021 ; Conference date: 30-08-2021 Through 03-09-2021",

year = "2021",

doi = "10.21437/Interspeech.2021-662",

language = "אנגלית",

series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

publisher = "International Speech Communication Association",

pages = "2328--2332",

booktitle = "22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021",

}

Eisenberg, A, Schwartz, B & Gannot, S 2021, Online blind audio source separation using recursive expectation-maximization. in 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 3, International Speech Communication Association, pp. 2328-2332, 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021, Brno, Czech Republic, 30/08/21. https://doi.org/10.21437/Interspeech.2021-662

Online blind audio source separation using recursive expectation-maximization. / Eisenberg, Aviad; Schwartz, Boaz; Gannot, Sharon.
22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021. International Speech Communication Association, 2021. p. 2328-2332 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 3).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Online blind audio source separation using recursive expectation-maximization

AU - Eisenberg, Aviad

AU - Schwartz, Boaz

AU - Gannot, Sharon

PY - 2021

Y1 - 2021

N2 - The challenging problem of online multi-microphone blind audio source separation (BASS) in noisy environment is addressed in this paper. We present a sequential, non-iterative, algorithm based on the recursive EM (REM) framework. In the proposed algorithm, the compete-data, which constitutes the separated sources and residual noise, is estimated in the E-step by applying a multichannel Wiener filter (MCWF); and the corresponding parameters, comprised of acoustic transfer functions (ATFs) relating the sources and the microphones and power spectral densities (PSDs) of the desired sources, are sequentially estimated in the M-step. The separated speech signals are further enhanced using matched-filter beamformers. The performance of the algorithm is demonstrated in terms of the separation capabilities, the resulting speech intelligibility and the ability to track the direction of arrival (DOA) of the moving sources.

AB - The challenging problem of online multi-microphone blind audio source separation (BASS) in noisy environment is addressed in this paper. We present a sequential, non-iterative, algorithm based on the recursive EM (REM) framework. In the proposed algorithm, the compete-data, which constitutes the separated sources and residual noise, is estimated in the E-step by applying a multichannel Wiener filter (MCWF); and the corresponding parameters, comprised of acoustic transfer functions (ATFs) relating the sources and the microphones and power spectral densities (PSDs) of the desired sources, are sequentially estimated in the M-step. The separated speech signals are further enhanced using matched-filter beamformers. The performance of the algorithm is demonstrated in terms of the separation capabilities, the resulting speech intelligibility and the ability to track the direction of arrival (DOA) of the moving sources.

KW - Multichannel Wiener filter beamforming

KW - Recursive expectation maximization

KW - blind audio source separation

UR - http://www.scopus.com/inward/record.url?scp=85119207004&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2021-662

DO - 10.21437/Interspeech.2021-662

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85119207004

T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SP - 2328

EP - 2332

BT - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021

PB - International Speech Communication Association

T2 - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021

Y2 - 30 August 2021 through 3 September 2021

ER -

Eisenberg A, Schwartz B, Gannot S. Online blind audio source separation using recursive expectation-maximization. In 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021. International Speech Communication Association. 2021. p. 2328-2332. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). doi: 10.21437/Interspeech.2021-662

Online blind audio source separation using recursive expectation-maximization

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this