Canonical correlation analysis in speech enhancement /

Saved in:
Bibliographic Details
Author / Creator:Benesty, Jacob, author.
Imprint:Cham, Switzerland : Springer, [2018]
©2018
Description:1 online resource
Language:English
Series:SpringerBriefs in electrical and computer engineering, 2191-8112
SpringerBriefs in electrical and computer engineering.
Subject:
Format: E-Resource Book
URL for this record:http://pi.lib.uchicago.edu/1001/cat/bib/11541595
Hidden Bibliographic Details
Other authors / contributors:Cohen, Israel, 1879-1961, author.
ISBN:9783319670201
3319670204
3319670190
9783319670195
Digital file characteristics:text file
PDF
Notes:Includes bibliographical references and index.
Print version record.
Summary:This book focuses on the application of canonical correlation analysis (CCA) to speech enhancement using the filtering approach. The authors explain how to derive different classes of time-domain and time-frequency-domain noise reduction filters, which are optimal from the CCA perspective for both single-channel and multichannel speech enhancement. Enhancement of noisy speech has been a challenging problem for many researchers over the past few decades and remains an active research area. Typically, speech enhancement algorithms operate in the short-time Fourier transform (STFT) domain, where the clean speech spectral coefficients are estimated using a multiplicative gain function. A filtering approach, which can be performed in the time domain or in the subband domain, obtains an estimate of the clean speech sample at every time instant or time-frequency bin by applying a filtering vector to the noisy speech vector. Compared to the multiplicative gain approach, the filtering approach more naturally takes into account the correlation of the speech signal in adjacent time frames. In this study, the authors pursue the filtering approach and show how to apply CCA to the speech enhancement problem. They also address the problem of adaptive beamforming from the CCA perspective, and show that the well-known Wiener and minimum variance distortionless response (MVDR) beamformers are particular cases of a general class of CCA-based adaptive beamformers.
Other form:Print version: 3319670190 9783319670195
Standard no.:10.1007/978-3-319-67020-1

MARC

LEADER 00000cam a2200000 i 4500
001 11541595
005 20210625185142.1
006 m o d
007 cr |n|||||||||
008 170906s2018 sz ob 001 0 eng d
015 |a GBB8O3444  |2 bnb 
016 7 |a 019182898  |2 Uk 
019 |a 1003205163  |a 1003253617  |a 1008870840  |a 1011791646  |a 1021252762 
020 |a 9783319670201  |q (electronic bk.) 
020 |a 3319670204  |q (electronic bk.) 
020 |z 3319670190 
020 |z 9783319670195 
024 7 |a 10.1007/978-3-319-67020-1  |2 doi 
035 |a (OCoLC)1003117721  |z (OCoLC)1003205163  |z (OCoLC)1003253617  |z (OCoLC)1008870840  |z (OCoLC)1011791646  |z (OCoLC)1021252762 
035 9 |a (OCLCCM-CC)1003117721 
037 |a com.springer.onix.9783319670201  |b Springer Nature 
040 |a YDX  |b eng  |e rda  |e pn  |c YDX  |d N$T  |d EBLCP  |d GW5XE  |d N$T  |d OCLCF  |d NJR  |d AZU  |d COO  |d IDB  |d UAB  |d MERUC  |d U3W  |d CAUOI  |d OCLCA  |d VT2  |d MERER  |d OCLCQ  |d EZ9  |d WYU  |d OCLCQ  |d LVT  |d UKMGB  |d AUD  |d OCLCQ 
049 |a MAIN 
050 4 |a TK7882.S65 
072 7 |a COM  |x 000000  |2 bisacsh 
072 7 |a TTBM  |2 bicssc 
072 7 |a UYS  |2 bicssc 
100 1 |a Benesty, Jacob,  |e author.  |0 http://id.loc.gov/authorities/names/n00001625 
245 1 0 |a Canonical correlation analysis in speech enhancement /  |c Jacob Benesty, Israel Cohen. 
264 1 |a Cham, Switzerland :  |b Springer,  |c [2018] 
264 4 |c ©2018 
300 |a 1 online resource 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
347 |a text file 
347 |b PDF 
490 1 |a SpringerBriefs in electrical and computer engineering,  |x 2191-8112 
505 0 |a Abstract; 1 Introduction; 1.1 Canonical Correlation Analysis and Speech Enhancement; 1.2 Organization of the Work; References; 2 Canonical Correlation Analysis; 2.1 Preliminaries; 2.2 How CCA Works; 2.3 The Singular Case; References; 3 Single-Channel Speech Enhancement in the Time Domain; 3.1 Signal Model and Problem Formulation; 3.2 Canonical Linear Filtering; 3.3 Performance Measures; 3.4 Optimal Canonical Filters from the Desired and Noisy Signals; 3.5 Optimal Canonical Filters from the Noise and Noisy Signals; References; 4 Single-Channel Speech Enhancement in the STFT Domain. 
505 8 |a 4.1 Signal Model and Problem Formulation4.2 Canonical Linear Filtering; 4.3 Performance Measures; 4.4 Optimal Canonical Filters from the Desired and Noisy Signals; 4.5 Optimal Canonical Filters from the Noise and Noisy Signals; References; 5 Multichannel Speech Enhancement in the Time Domain; 5.1 Signal Model and Problem Formulation; 5.2 Canonical Linear Filtering; 5.3 Performance Measures; 5.4 Optimal Canonical Filters from the Desired and Noisy Signals; 5.5 Optimal Canonical Filters from the Noise and Noisy Signals; 5.6 Other Possibilities; References. 
505 8 |a 6 Multichannel Speech Enhancement in the STFT Domain6.1 Signal Model and Problem Formulation; 6.2 Canonical Linear Filtering; 6.3 Performance Measures; 6.4 Optimal Canonical Filters from the Desired and Noisy Signals; 6.5 Optimal Canonical Filters from the Noise and Noisy Signals; 6.6 Other Possibilities; References; 7 Adaptive Beamforming; 7.1 Signal Model and Problem Formulation; 7.2 Canonical Linear Filtering; 7.3 Performance Measures; 7.4 Optimal Canonical Filters from the Desired and Noisy Signals; 7.5 Optimal Canonical Filters from the Noise and Noisy Signals; References; Index. 
504 |a Includes bibliographical references and index. 
588 0 |a Print version record. 
520 |a This book focuses on the application of canonical correlation analysis (CCA) to speech enhancement using the filtering approach. The authors explain how to derive different classes of time-domain and time-frequency-domain noise reduction filters, which are optimal from the CCA perspective for both single-channel and multichannel speech enhancement. Enhancement of noisy speech has been a challenging problem for many researchers over the past few decades and remains an active research area. Typically, speech enhancement algorithms operate in the short-time Fourier transform (STFT) domain, where the clean speech spectral coefficients are estimated using a multiplicative gain function. A filtering approach, which can be performed in the time domain or in the subband domain, obtains an estimate of the clean speech sample at every time instant or time-frequency bin by applying a filtering vector to the noisy speech vector. Compared to the multiplicative gain approach, the filtering approach more naturally takes into account the correlation of the speech signal in adjacent time frames. In this study, the authors pursue the filtering approach and show how to apply CCA to the speech enhancement problem. They also address the problem of adaptive beamforming from the CCA perspective, and show that the well-known Wiener and minimum variance distortionless response (MVDR) beamformers are particular cases of a general class of CCA-based adaptive beamformers. 
650 0 |a Speech processing systems.  |0 http://id.loc.gov/authorities/subjects/sh85126450 
650 7 |a COMPUTERS  |x General.  |2 bisacsh 
650 7 |a Imaging systems & technology.  |2 bicssc 
650 7 |a Speech processing systems.  |2 fast  |0 (OCoLC)fst01129243 
655 4 |a Electronic books. 
700 1 |a Cohen, Israel,  |d 1879-1961,  |e author. 
776 0 8 |i Print version:  |z 3319670190  |z 9783319670195  |w (OCoLC)996418313 
830 0 |a SpringerBriefs in electrical and computer engineering.  |0 http://id.loc.gov/authorities/names/no2011108018 
903 |a HeVa 
929 |a oclccm 
999 f f |i c643d545-f442-54fa-9084-b4715aea75e4  |s a3298fac-b7fe-5499-9534-1facc1ecddc4 
928 |t Library of Congress classification  |a TK7882.S65  |l Online  |c UC-FullText  |u https://link.springer.com/10.1007/978-3-319-67020-1  |z Springer Nature  |g ebooks  |i 12548373