On the use of PCA in GMM and AR-vector models for text independent speaker verification

This paper examines the role of the principal components analysis (PCA) on the performance of two classification systems for text independent speaker verification: the Gaussian mixture model (GMM) and the AR-vector model. The use of the PCA transform resulted in an improvement in the performance of...

Full description

Saved in:
Bibliographic Details
Main Authors: de Lima, C.B., Alcaim, A., Apolinario, J.A.
Format: Conference Proceeding
Language:English
Subjects:
Covariance matrix
Error analysis
Hidden Markov models
Loudspeakers
Principal component analysis
Speaker recognition
Speech
Telephony
Testing
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 598 vol.2
container_issue
container_start_page 595
container_title
container_volume 2
creator de Lima, C.B.
Alcaim, A.
Apolinario, J.A.
description This paper examines the role of the principal components analysis (PCA) on the performance of two classification systems for text independent speaker verification: the Gaussian mixture model (GMM) and the AR-vector model. The use of the PCA transform resulted in an improvement in the performance of the GMM for training times of 60 s and 30 s. However, the advantage of using PCA was not observed for the AR-vector model. For the case of 10 s training time, there was no benefit in using PCA even with GMM. In this situation, the AR-vector is superior for a 10 s test and worse for a 3 s test. In this latter case, however, all systems yielded error rates above 7%.
doi_str_mv 10.1109/ICDSP.2002.1028160
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1028160</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1028160</ieee_id><sourcerecordid>1028160</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-7441b3c8127b2a3a1ae51847a1c5563d2eda1edf64ab50058a6e639a1aa8bace3</originalsourceid><addsrcrecordid>eNotT21LwzAYDIigzP4B_ZI_0JonaZr0Y6k6BxsbvuDH8bR9itGtHU0c7t8bcMdxdx-Og2PsFkQGIMr7Rf3wusmkEDIDIS0U4oIlpbEiUhktFFyxxPsvEZHr3BpzzT7WAw-fxH888bHnm7ribuDz1Yrj0PHqJT1SG8aJ78eOdp73MQb6DbHU0YGiDIH7A-E3TfxIk-tdi8GNww277HHnKTn7jL0_Pb7Vz-lyPV_U1TJ1YHRITZ5Do1oL0jQSFQKSBpsbhFbrQnWSOgTq-iLHRguhLRZUqDL20DbYkpqxu_9dR0Tbw-T2OJ225_vqD4-lT-Y</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>On the use of PCA in GMM and AR-vector models for text independent speaker verification</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>de Lima, C.B. ; Alcaim, A. ; Apolinario, J.A.</creator><creatorcontrib>de Lima, C.B. ; Alcaim, A. ; Apolinario, J.A.</creatorcontrib><description>This paper examines the role of the principal components analysis (PCA) on the performance of two classification systems for text independent speaker verification: the Gaussian mixture model (GMM) and the AR-vector model. The use of the PCA transform resulted in an improvement in the performance of the GMM for training times of 60 s and 30 s. However, the advantage of using PCA was not observed for the AR-vector model. For the case of 10 s training time, there was no benefit in using PCA even with GMM. In this situation, the AR-vector is superior for a 10 s test and worse for a 3 s test. In this latter case, however, all systems yielded error rates above 7%.</description><identifier>ISBN: 9780780375031</identifier><identifier>ISBN: 0780375033</identifier><identifier>DOI: 10.1109/ICDSP.2002.1028160</identifier><language>eng</language><publisher>IEEE</publisher><subject>Covariance matrix ; Error analysis ; Hidden Markov models ; Loudspeakers ; Principal component analysis ; Speaker recognition ; Speech ; Telephony ; Testing ; Training data</subject><ispartof>2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628), 2002, Vol.2, p.595-598 vol.2</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1028160$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1028160$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>de Lima, C.B.</creatorcontrib><creatorcontrib>Alcaim, A.</creatorcontrib><creatorcontrib>Apolinario, J.A.</creatorcontrib><title>On the use of PCA in GMM and AR-vector models for text independent speaker verification</title><title>2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)</title><addtitle>ICDSP</addtitle><description>This paper examines the role of the principal components analysis (PCA) on the performance of two classification systems for text independent speaker verification: the Gaussian mixture model (GMM) and the AR-vector model. The use of the PCA transform resulted in an improvement in the performance of the GMM for training times of 60 s and 30 s. However, the advantage of using PCA was not observed for the AR-vector model. For the case of 10 s training time, there was no benefit in using PCA even with GMM. In this situation, the AR-vector is superior for a 10 s test and worse for a 3 s test. In this latter case, however, all systems yielded error rates above 7%.</description><subject>Covariance matrix</subject><subject>Error analysis</subject><subject>Hidden Markov models</subject><subject>Loudspeakers</subject><subject>Principal component analysis</subject><subject>Speaker recognition</subject><subject>Speech</subject><subject>Telephony</subject><subject>Testing</subject><subject>Training data</subject><isbn>9780780375031</isbn><isbn>0780375033</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2002</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotT21LwzAYDIigzP4B_ZI_0JonaZr0Y6k6BxsbvuDH8bR9itGtHU0c7t8bcMdxdx-Og2PsFkQGIMr7Rf3wusmkEDIDIS0U4oIlpbEiUhktFFyxxPsvEZHr3BpzzT7WAw-fxH888bHnm7ribuDz1Yrj0PHqJT1SG8aJ78eOdp73MQb6DbHU0YGiDIH7A-E3TfxIk-tdi8GNww277HHnKTn7jL0_Pb7Vz-lyPV_U1TJ1YHRITZ5Do1oL0jQSFQKSBpsbhFbrQnWSOgTq-iLHRguhLRZUqDL20DbYkpqxu_9dR0Tbw-T2OJ225_vqD4-lT-Y</recordid><startdate>2002</startdate><enddate>2002</enddate><creator>de Lima, C.B.</creator><creator>Alcaim, A.</creator><creator>Apolinario, J.A.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>2002</creationdate><title>On the use of PCA in GMM and AR-vector models for text independent speaker verification</title><author>de Lima, C.B. ; Alcaim, A. ; Apolinario, J.A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-7441b3c8127b2a3a1ae51847a1c5563d2eda1edf64ab50058a6e639a1aa8bace3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2002</creationdate><topic>Covariance matrix</topic><topic>Error analysis</topic><topic>Hidden Markov models</topic><topic>Loudspeakers</topic><topic>Principal component analysis</topic><topic>Speaker recognition</topic><topic>Speech</topic><topic>Telephony</topic><topic>Testing</topic><topic>Training data</topic><toplevel>online_resources</toplevel><creatorcontrib>de Lima, C.B.</creatorcontrib><creatorcontrib>Alcaim, A.</creatorcontrib><creatorcontrib>Apolinario, J.A.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEL</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>de Lima, C.B.</au><au>Alcaim, A.</au><au>Apolinario, J.A.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>On the use of PCA in GMM and AR-vector models for text independent speaker verification</atitle><btitle>2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)</btitle><stitle>ICDSP</stitle><date>2002</date><risdate>2002</risdate><volume>2</volume><spage>595</spage><epage>598 vol.2</epage><pages>595-598 vol.2</pages><isbn>9780780375031</isbn><isbn>0780375033</isbn><abstract>This paper examines the role of the principal components analysis (PCA) on the performance of two classification systems for text independent speaker verification: the Gaussian mixture model (GMM) and the AR-vector model. The use of the PCA transform resulted in an improvement in the performance of the GMM for training times of 60 s and 30 s. However, the advantage of using PCA was not observed for the AR-vector model. For the case of 10 s training time, there was no benefit in using PCA even with GMM. In this situation, the AR-vector is superior for a 10 s test and worse for a 3 s test. In this latter case, however, all systems yielded error rates above 7%.</abstract><pub>IEEE</pub><doi>10.1109/ICDSP.2002.1028160</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9780780375031
ispartof 2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628), 2002, Vol.2, p.595-598 vol.2
issn
language eng
recordid cdi_ieee_primary_1028160
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Covariance matrix
Error analysis
Hidden Markov models
Loudspeakers
Principal component analysis
Speaker recognition
Speech
Telephony
Testing
Training data
title On the use of PCA in GMM and AR-vector models for text independent speaker verification
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T03%3A26%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=On%20the%20use%20of%20PCA%20in%20GMM%20and%20AR-vector%20models%20for%20text%20independent%20speaker%20verification&rft.btitle=2002%2014th%20International%20Conference%20on%20Digital%20Signal%20Processing%20Proceedings.%20DSP%202002%20(Cat.%20No.02TH8628)&rft.au=de%20Lima,%20C.B.&rft.date=2002&rft.volume=2&rft.spage=595&rft.epage=598%20vol.2&rft.pages=595-598%20vol.2&rft.isbn=9780780375031&rft.isbn_list=0780375033&rft_id=info:doi/10.1109/ICDSP.2002.1028160&rft_dat=%3Cieee_6IE%3E1028160%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-7441b3c8127b2a3a1ae51847a1c5563d2eda1edf64ab50058a6e639a1aa8bace3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1028160&rfr_iscdi=true