A Weighted Multichannel Wiener Filter and its Decomposition to LCMV Beam Former and Post-Filter for Source Separation and Noise Reduction

Aviel Adler; Ofer Schwartz; Sharon Gannot

doi:10.1109/icsee.2018.8646309

A Weighted Multichannel Wiener Filter and its Decomposition to LCMV Beam Former and Post-Filter for Source Separation and Noise Reduction

Aviel Adler, Ofer Schwartz, Sharon Gannot

Bar-Ilan University - The Alexander Kofkin Faculty of Engineering

Bar-Ilan University

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

Abstract

Speech enhancement and source separation are well-known challenges in the context of hands-free communication and automatic speech recognition. The multichannel Wiener filter (MCWF) that satisfies the minimum mean square error (MMSE) criterion, is a fundamental speech enhancement tool. However, it can suffer from speech distortion, especially when the noise level is high. The speech distortion weighted multichannel Wiener filter (SDW-MWF) was therefore proposed to control the tradeoff between noise reduction and speech distortion for the single-speaker case. In this paper, we generalize this estimator and propose a method for controlling this tradeoff in the multi-speaker case. The proposed estimator is decomposed into two successive stages: 1) a multi-speaker linearly constrained minimum variance (LCMV), which is solely determined by the spatial characteristics of the speakers; and 2) a multi-speaker Wiener postfilter (PF), which is responsible for reducing the residual noise. The proposed PF consists of several controlling parameters that can almost independently control the tradeoff between the distortion of each speaker and the total noise reduction.

Original language	English
Title of host publication	2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538663783
DOIs	https://doi.org/10.1109/icsee.2018.8646309
State	Published - 2 Jul 2018
Event	2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018 - Eilat, Israel Duration: 12 Dec 2018 → 14 Dec 2018

Publication series

Name	2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018

Conference

Conference	2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018
Country/Territory	Israel
City	Eilat
Period	12/12/18 → 14/12/18

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering

Access to Document

10.1109/icsee.2018.8646309

Cite this

Adler, A., Schwartz, O., & Gannot, S. (2018). A Weighted Multichannel Wiener Filter and its Decomposition to LCMV Beam Former and Post-Filter for Source Separation and Noise Reduction. In 2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018 Article 8646309 (2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/icsee.2018.8646309

Adler, Aviel ; Schwartz, Ofer ; Gannot, Sharon. / A Weighted Multichannel Wiener Filter and its Decomposition to LCMV Beam Former and Post-Filter for Source Separation and Noise Reduction. 2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018. Institute of Electrical and Electronics Engineers Inc., 2018. (2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018).

@inproceedings{549855930a024e309a073fecd755202b,

title = "A Weighted Multichannel Wiener Filter and its Decomposition to LCMV Beam Former and Post-Filter for Source Separation and Noise Reduction",

abstract = "Speech enhancement and source separation are well-known challenges in the context of hands-free communication and automatic speech recognition. The multichannel Wiener filter (MCWF) that satisfies the minimum mean square error (MMSE) criterion, is a fundamental speech enhancement tool. However, it can suffer from speech distortion, especially when the noise level is high. The speech distortion weighted multichannel Wiener filter (SDW-MWF) was therefore proposed to control the tradeoff between noise reduction and speech distortion for the single-speaker case. In this paper, we generalize this estimator and propose a method for controlling this tradeoff in the multi-speaker case. The proposed estimator is decomposed into two successive stages: 1) a multi-speaker linearly constrained minimum variance (LCMV), which is solely determined by the spatial characteristics of the speakers; and 2) a multi-speaker Wiener postfilter (PF), which is responsible for reducing the residual noise. The proposed PF consists of several controlling parameters that can almost independently control the tradeoff between the distortion of each speaker and the total noise reduction.",

author = "Aviel Adler and Ofer Schwartz and Sharon Gannot",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018 ; Conference date: 12-12-2018 Through 14-12-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/icsee.2018.8646309",

language = "الإنجليزيّة",

series = "2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018",

address = "الولايات المتّحدة",

}

Adler, A, Schwartz, O & Gannot, S 2018, A Weighted Multichannel Wiener Filter and its Decomposition to LCMV Beam Former and Post-Filter for Source Separation and Noise Reduction. in 2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018., 8646309, 2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018, Institute of Electrical and Electronics Engineers Inc., 2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018, Eilat, Israel, 12/12/18. https://doi.org/10.1109/icsee.2018.8646309

A Weighted Multichannel Wiener Filter and its Decomposition to LCMV Beam Former and Post-Filter for Source Separation and Noise Reduction. / Adler, Aviel; Schwartz, Ofer; Gannot, Sharon.
2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018. Institute of Electrical and Electronics Engineers Inc., 2018. 8646309 (2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018).

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

TY - GEN

T1 - A Weighted Multichannel Wiener Filter and its Decomposition to LCMV Beam Former and Post-Filter for Source Separation and Noise Reduction

AU - Adler, Aviel

AU - Schwartz, Ofer

AU - Gannot, Sharon

PY - 2018/7/2

Y1 - 2018/7/2

N2 - Speech enhancement and source separation are well-known challenges in the context of hands-free communication and automatic speech recognition. The multichannel Wiener filter (MCWF) that satisfies the minimum mean square error (MMSE) criterion, is a fundamental speech enhancement tool. However, it can suffer from speech distortion, especially when the noise level is high. The speech distortion weighted multichannel Wiener filter (SDW-MWF) was therefore proposed to control the tradeoff between noise reduction and speech distortion for the single-speaker case. In this paper, we generalize this estimator and propose a method for controlling this tradeoff in the multi-speaker case. The proposed estimator is decomposed into two successive stages: 1) a multi-speaker linearly constrained minimum variance (LCMV), which is solely determined by the spatial characteristics of the speakers; and 2) a multi-speaker Wiener postfilter (PF), which is responsible for reducing the residual noise. The proposed PF consists of several controlling parameters that can almost independently control the tradeoff between the distortion of each speaker and the total noise reduction.

AB - Speech enhancement and source separation are well-known challenges in the context of hands-free communication and automatic speech recognition. The multichannel Wiener filter (MCWF) that satisfies the minimum mean square error (MMSE) criterion, is a fundamental speech enhancement tool. However, it can suffer from speech distortion, especially when the noise level is high. The speech distortion weighted multichannel Wiener filter (SDW-MWF) was therefore proposed to control the tradeoff between noise reduction and speech distortion for the single-speaker case. In this paper, we generalize this estimator and propose a method for controlling this tradeoff in the multi-speaker case. The proposed estimator is decomposed into two successive stages: 1) a multi-speaker linearly constrained minimum variance (LCMV), which is solely determined by the spatial characteristics of the speakers; and 2) a multi-speaker Wiener postfilter (PF), which is responsible for reducing the residual noise. The proposed PF consists of several controlling parameters that can almost independently control the tradeoff between the distortion of each speaker and the total noise reduction.

UR - http://www.scopus.com/inward/record.url?scp=85063145614&partnerID=8YFLogxK

U2 - 10.1109/icsee.2018.8646309

DO - 10.1109/icsee.2018.8646309

M3 - منشور من مؤتمر

T3 - 2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018

BT - 2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018

Y2 - 12 December 2018 through 14 December 2018

ER -

Adler A, Schwartz O, Gannot S. A Weighted Multichannel Wiener Filter and its Decomposition to LCMV Beam Former and Post-Filter for Source Separation and Noise Reduction. In 2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018. Institute of Electrical and Electronics Engineers Inc. 2018. 8646309. (2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018). doi: 10.1109/icsee.2018.8646309

A Weighted Multichannel Wiener Filter and its Decomposition to LCMV Beam Former and Post-Filter for Source Separation and Noise Reduction

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this