Emotional speaker verification with linear adaptation

Speaker verification suffers from significant performance degradation on emotional speech. We present an adaptation approach based on maximum likelihood linear regression (MLLR) and its feature-space variant, CMLLR. Our preliminary experiments demonstrate that this approach leads to considerable per...

Full description

Saved in:
Bibliographic Details
Main Authors: Fanhu Bie, Dong Wang, Zheng, Thomas Fang, Ruxin Chen
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
Adaptation models
emotional speech
Hidden Markov models
MLLR
speaker verification
Speech
Training
Transforms
Vectors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 94
container_issue
container_start_page 91
container_title
container_volume
creator Fanhu Bie
Dong Wang
Zheng, Thomas Fang
Ruxin Chen
description Speaker verification suffers from significant performance degradation on emotional speech. We present an adaptation approach based on maximum likelihood linear regression (MLLR) and its feature-space variant, CMLLR. Our preliminary experiments demonstrate that this approach leads to considerable performance improvement, particularly with CMLLR (about 10% relative EER reduction in average). We also find that the performance gain can be significantly increased with a large set of training data for the transform estimation.
doi_str_mv 10.1109/ChinaSIP.2013.6625304
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6625304</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6625304</ieee_id><sourcerecordid>6625304</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-d6af387a32b6945e8c6a8a9fc4b9336554af901a9767576733693d3ad3d844d73</originalsourceid><addsrcrecordid>eNotz81Kw0AUBeBxISg1TyBCXiDxTu783aWEqoWCgt2X28wMHU3TMAmKb2_VLg4HvsWBI8SdhFpKoPt2nwZ-W73WDUisjWk0groQBVknlSWSoFBdiWKa3gFAWquR8Fro5eE4p-PAfTmNgT9CLj9DTjF1_MvlV5r3ZZ-GwLlkz-P8xzfiMnI_heLcC7F5XG7a52r98rRqH9ZVIpgrbziis4zNzpDSwXWGHVPs1I4QjdaKI4FkssbqU05G6JE9eqeUt7gQt_-zKYSwHXM6cP7enr_hD4tyRZc</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Emotional speaker verification with linear adaptation</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Fanhu Bie ; Dong Wang ; Zheng, Thomas Fang ; Ruxin Chen</creator><creatorcontrib>Fanhu Bie ; Dong Wang ; Zheng, Thomas Fang ; Ruxin Chen</creatorcontrib><description>Speaker verification suffers from significant performance degradation on emotional speech. We present an adaptation approach based on maximum likelihood linear regression (MLLR) and its feature-space variant, CMLLR. Our preliminary experiments demonstrate that this approach leads to considerable performance improvement, particularly with CMLLR (about 10% relative EER reduction in average). We also find that the performance gain can be significantly increased with a large set of training data for the transform estimation.</description><identifier>EISBN: 9781479910434</identifier><identifier>EISBN: 1479910430</identifier><identifier>DOI: 10.1109/ChinaSIP.2013.6625304</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acoustics ; Adaptation models ; emotional speech ; Hidden Markov models ; MLLR ; speaker verification ; Speech ; Training ; Transforms ; Vectors</subject><ispartof>2013 IEEE China Summit and International Conference on Signal and Information Processing, 2013, p.91-94</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/6625304$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6625304$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Fanhu Bie</creatorcontrib><creatorcontrib>Dong Wang</creatorcontrib><creatorcontrib>Zheng, Thomas Fang</creatorcontrib><creatorcontrib>Ruxin Chen</creatorcontrib><title>Emotional speaker verification with linear adaptation</title><title>2013 IEEE China Summit and International Conference on Signal and Information Processing</title><addtitle>ChinaSIP</addtitle><description>Speaker verification suffers from significant performance degradation on emotional speech. We present an adaptation approach based on maximum likelihood linear regression (MLLR) and its feature-space variant, CMLLR. Our preliminary experiments demonstrate that this approach leads to considerable performance improvement, particularly with CMLLR (about 10% relative EER reduction in average). We also find that the performance gain can be significantly increased with a large set of training data for the transform estimation.</description><subject>Acoustics</subject><subject>Adaptation models</subject><subject>emotional speech</subject><subject>Hidden Markov models</subject><subject>MLLR</subject><subject>speaker verification</subject><subject>Speech</subject><subject>Training</subject><subject>Transforms</subject><subject>Vectors</subject><isbn>9781479910434</isbn><isbn>1479910430</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2013</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotz81Kw0AUBeBxISg1TyBCXiDxTu783aWEqoWCgt2X28wMHU3TMAmKb2_VLg4HvsWBI8SdhFpKoPt2nwZ-W73WDUisjWk0groQBVknlSWSoFBdiWKa3gFAWquR8Fro5eE4p-PAfTmNgT9CLj9DTjF1_MvlV5r3ZZ-GwLlkz-P8xzfiMnI_heLcC7F5XG7a52r98rRqH9ZVIpgrbziis4zNzpDSwXWGHVPs1I4QjdaKI4FkssbqU05G6JE9eqeUt7gQt_-zKYSwHXM6cP7enr_hD4tyRZc</recordid><startdate>201307</startdate><enddate>201307</enddate><creator>Fanhu Bie</creator><creator>Dong Wang</creator><creator>Zheng, Thomas Fang</creator><creator>Ruxin Chen</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201307</creationdate><title>Emotional speaker verification with linear adaptation</title><author>Fanhu Bie ; Dong Wang ; Zheng, Thomas Fang ; Ruxin Chen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-d6af387a32b6945e8c6a8a9fc4b9336554af901a9767576733693d3ad3d844d73</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Acoustics</topic><topic>Adaptation models</topic><topic>emotional speech</topic><topic>Hidden Markov models</topic><topic>MLLR</topic><topic>speaker verification</topic><topic>Speech</topic><topic>Training</topic><topic>Transforms</topic><topic>Vectors</topic><toplevel>online_resources</toplevel><creatorcontrib>Fanhu Bie</creatorcontrib><creatorcontrib>Dong Wang</creatorcontrib><creatorcontrib>Zheng, Thomas Fang</creatorcontrib><creatorcontrib>Ruxin Chen</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>IEEE Electronic Library Online</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>Fanhu Bie</au><au>Dong Wang</au><au>Zheng, Thomas Fang</au><au>Ruxin Chen</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Emotional speaker verification with linear adaptation</atitle><btitle>2013 IEEE China Summit and International Conference on Signal and Information Processing</btitle><stitle>ChinaSIP</stitle><date>2013-07</date><risdate>2013</risdate><spage>91</spage><epage>94</epage><pages>91-94</pages><eisbn>9781479910434</eisbn><eisbn>1479910430</eisbn><abstract>Speaker verification suffers from significant performance degradation on emotional speech. We present an adaptation approach based on maximum likelihood linear regression (MLLR) and its feature-space variant, CMLLR. Our preliminary experiments demonstrate that this approach leads to considerable performance improvement, particularly with CMLLR (about 10% relative EER reduction in average). We also find that the performance gain can be significantly increased with a large set of training data for the transform estimation.</abstract><pub>IEEE</pub><doi>10.1109/ChinaSIP.2013.6625304</doi><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISBN: 9781479910434
ispartof 2013 IEEE China Summit and International Conference on Signal and Information Processing, 2013, p.91-94
issn
language eng
recordid cdi_ieee_primary_6625304
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Acoustics
Adaptation models
emotional speech
Hidden Markov models
MLLR
speaker verification
Speech
Training
Transforms
Vectors
title Emotional speaker verification with linear adaptation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-21T17%3A07%3A27IST&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=Emotional%20speaker%20verification%20with%20linear%20adaptation&rft.btitle=2013%20IEEE%20China%20Summit%20and%20International%20Conference%20on%20Signal%20and%20Information%20Processing&rft.au=Fanhu%20Bie&rft.date=2013-07&rft.spage=91&rft.epage=94&rft.pages=91-94&rft_id=info:doi/10.1109/ChinaSIP.2013.6625304&rft.eisbn=9781479910434&rft.eisbn_list=1479910430&rft_dat=%3Cieee_6IE%3E6625304%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-d6af387a32b6945e8c6a8a9fc4b9336554af901a9767576733693d3ad3d844d73%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=6625304&rfr_iscdi=true