Speech Enhancement: A Signal Subspace Perspective

Jacob Benesty, Jesper Rindom Jensen, Mads Græsbøll Christensen, Jingdong Chen

Research output: Book/ReportBookResearchpeer-review

Abstract

Speech enhancement is a classical problem in signal processing, yet still largely unsolved. Two of the conventional approaches for solving this problem are linear filtering, like the classical Wiener filter, and subspace methods. These approaches have traditionally been treated as different classes of methods and have been introduced in somewhat different contexts. Linear filtering methods originate in stochastic processes, while subspace methods have largely been based on developments in numerical linear algebra and matrix approximation theory.

This book bridges the gap between these two classes of methods by showing how the ideas behind subspace methods can be incorporated into traditional linear filtering. In the context of subspace methods, the enhancement problem can then be seen as a classical linear filter design problem. This means that various solutions can more easily be compared and their performance bounded and assessed in terms of noise reduction and speech distortion. The book shows how various filter designs can be obtained in this framework, including the maximum SNR, Wiener, LCMV, and MVDR filters, and how these can be applied in various contexts, like in single-channel and multichannel speech enhancement, and in both the time and frequency domains.
Original languageEnglish
PublisherAcademic Press
Edition1
Number of pages138
ISBN (Print)978-0-12-800139-4
DOIs
Publication statusPublished - 2014

Fingerprint

Speech enhancement
Approximation theory
Linear algebra
Noise abatement
Random processes
Signal processing

Cite this

Benesty, Jacob ; Jensen, Jesper Rindom ; Christensen, Mads Græsbøll ; Chen, Jingdong. / Speech Enhancement : A Signal Subspace Perspective. 1 ed. Academic Press, 2014. 138 p.
@book{1677daf6f7e24f05a1d842dc13634683,
title = "Speech Enhancement: A Signal Subspace Perspective",
abstract = "Speech enhancement is a classical problem in signal processing, yet still largely unsolved. Two of the conventional approaches for solving this problem are linear filtering, like the classical Wiener filter, and subspace methods. These approaches have traditionally been treated as different classes of methods and have been introduced in somewhat different contexts. Linear filtering methods originate in stochastic processes, while subspace methods have largely been based on developments in numerical linear algebra and matrix approximation theory.This book bridges the gap between these two classes of methods by showing how the ideas behind subspace methods can be incorporated into traditional linear filtering. In the context of subspace methods, the enhancement problem can then be seen as a classical linear filter design problem. This means that various solutions can more easily be compared and their performance bounded and assessed in terms of noise reduction and speech distortion. The book shows how various filter designs can be obtained in this framework, including the maximum SNR, Wiener, LCMV, and MVDR filters, and how these can be applied in various contexts, like in single-channel and multichannel speech enhancement, and in both the time and frequency domains.",
keywords = "Speech enhancement, Noise reduction, Wiener, Linearly constrained minimum variance, Minimum variance distortionless response, Maximum SNR, Joint diagonlization, Tradeoff",
author = "Jacob Benesty and Jensen, {Jesper Rindom} and Christensen, {Mads Gr{\ae}sb{\o}ll} and Jingdong Chen",
year = "2014",
doi = "10.1016/B978-0-12-800139-4.00009-8",
language = "English",
isbn = "978-0-12-800139-4",
publisher = "Academic Press",
address = "United States",
edition = "1",

}

Speech Enhancement : A Signal Subspace Perspective. / Benesty, Jacob; Jensen, Jesper Rindom; Christensen, Mads Græsbøll; Chen, Jingdong.

1 ed. Academic Press, 2014. 138 p.

Research output: Book/ReportBookResearchpeer-review

TY - BOOK

T1 - Speech Enhancement

T2 - A Signal Subspace Perspective

AU - Benesty, Jacob

AU - Jensen, Jesper Rindom

AU - Christensen, Mads Græsbøll

AU - Chen, Jingdong

PY - 2014

Y1 - 2014

N2 - Speech enhancement is a classical problem in signal processing, yet still largely unsolved. Two of the conventional approaches for solving this problem are linear filtering, like the classical Wiener filter, and subspace methods. These approaches have traditionally been treated as different classes of methods and have been introduced in somewhat different contexts. Linear filtering methods originate in stochastic processes, while subspace methods have largely been based on developments in numerical linear algebra and matrix approximation theory.This book bridges the gap between these two classes of methods by showing how the ideas behind subspace methods can be incorporated into traditional linear filtering. In the context of subspace methods, the enhancement problem can then be seen as a classical linear filter design problem. This means that various solutions can more easily be compared and their performance bounded and assessed in terms of noise reduction and speech distortion. The book shows how various filter designs can be obtained in this framework, including the maximum SNR, Wiener, LCMV, and MVDR filters, and how these can be applied in various contexts, like in single-channel and multichannel speech enhancement, and in both the time and frequency domains.

AB - Speech enhancement is a classical problem in signal processing, yet still largely unsolved. Two of the conventional approaches for solving this problem are linear filtering, like the classical Wiener filter, and subspace methods. These approaches have traditionally been treated as different classes of methods and have been introduced in somewhat different contexts. Linear filtering methods originate in stochastic processes, while subspace methods have largely been based on developments in numerical linear algebra and matrix approximation theory.This book bridges the gap between these two classes of methods by showing how the ideas behind subspace methods can be incorporated into traditional linear filtering. In the context of subspace methods, the enhancement problem can then be seen as a classical linear filter design problem. This means that various solutions can more easily be compared and their performance bounded and assessed in terms of noise reduction and speech distortion. The book shows how various filter designs can be obtained in this framework, including the maximum SNR, Wiener, LCMV, and MVDR filters, and how these can be applied in various contexts, like in single-channel and multichannel speech enhancement, and in both the time and frequency domains.

KW - Speech enhancement

KW - Noise reduction

KW - Wiener

KW - Linearly constrained minimum variance

KW - Minimum variance distortionless response

KW - Maximum SNR

KW - Joint diagonlization

KW - Tradeoff

U2 - 10.1016/B978-0-12-800139-4.00009-8

DO - 10.1016/B978-0-12-800139-4.00009-8

M3 - Book

SN - 978-0-12-800139-4

BT - Speech Enhancement

PB - Academic Press

ER -