Speaker adaptations in sparse training data for improved speaker verification
The over-training problem in speaker verification occurs when modelling a speaker with sparse training data. The authors propose to solve this problem by employing effective speaker adaptations, using a hybrid version of the maximum a posteriori and maximum likelihood linear regression methods. Expe...
Gespeichert in:
| Veröffentlicht in: | Electronics letters 2000-02, Vol.36 (4), p.1-1 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1 |
|---|---|
| container_issue | 4 |
| container_start_page | 1 |
| container_title | Electronics letters |
| container_volume | 36 |
| creator | Ahn, Sungjoo Ko, Hanseok |
| description | The over-training problem in speaker verification occurs when modelling a speaker with sparse training data. The authors propose to solve this problem by employing effective speaker adaptations, using a hybrid version of the maximum a posteriori and maximum likelihood linear regression methods. Experimental results show that the speaker verification system, using the proposed hybrid adaptation scheme, outperforms systems based on speaker models without adaptation by a factor of up to 5. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_miscellaneous_1651420626</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1651420626</sourcerecordid><originalsourceid>FETCH-LOGICAL-p616-35593d50534476e92f7177dce389e1d7af2452af8907233caddb6458590c67c3</originalsourceid><addsrcrecordid>eNpdkE1LAzEYhIMoWKv_IeDFy0K-3mRzlOIXVDzUg7fymg9J3e6uyW5_v8F66mkYeGYY5owsuATWWM4_zsmCMS4b4FZdkqtSdtUKa82CvG7GgN8hU_Q4TjiloS809bSMmEugU8bUp_6LepyQxiHTtB_zcAi-EsfgIeQUk_uLXpOLiF0JN_-6JJvHh_fVc7N-e3pZ3a-bUXPdSAArPTCQShkdrIiGG-NdkK0N3BuMQoHA2FpmhJQOvf_UClqwzGnj5JLcHVvrkp85lGm7T8WFrsM-DHPZcg1cCaaFrujtCbob5tzXbZUSoDToeswvqX9YAQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1625465601</pqid></control><display><type>article</type><title>Speaker adaptations in sparse training data for improved speaker verification</title><source>Alma/SFX Local Collection</source><creator>Ahn, Sungjoo ; Ko, Hanseok</creator><creatorcontrib>Ahn, Sungjoo ; Ko, Hanseok</creatorcontrib><description>The over-training problem in speaker verification occurs when modelling a speaker with sparse training data. The authors propose to solve this problem by employing effective speaker adaptations, using a hybrid version of the maximum a posteriori and maximum likelihood linear regression methods. Experimental results show that the speaker verification system, using the proposed hybrid adaptation scheme, outperforms systems based on speaker models without adaptation by a factor of up to 5.</description><identifier>ISSN: 0013-5194</identifier><identifier>EISSN: 1350-911X</identifier><identifier>CODEN: ELLEAK</identifier><language>eng</language><publisher>Stevenage: John Wiley & Sons, Inc</publisher><subject>Adaptation ; Mathematical models ; Modelling ; Program verification (computers) ; Regression ; Training</subject><ispartof>Electronics letters, 2000-02, Vol.36 (4), p.1-1</ispartof><rights>Copyright The Institution of Engineering & Technology Feb 17, 2000</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784</link.rule.ids></links><search><creatorcontrib>Ahn, Sungjoo</creatorcontrib><creatorcontrib>Ko, Hanseok</creatorcontrib><title>Speaker adaptations in sparse training data for improved speaker verification</title><title>Electronics letters</title><description>The over-training problem in speaker verification occurs when modelling a speaker with sparse training data. The authors propose to solve this problem by employing effective speaker adaptations, using a hybrid version of the maximum a posteriori and maximum likelihood linear regression methods. Experimental results show that the speaker verification system, using the proposed hybrid adaptation scheme, outperforms systems based on speaker models without adaptation by a factor of up to 5.</description><subject>Adaptation</subject><subject>Mathematical models</subject><subject>Modelling</subject><subject>Program verification (computers)</subject><subject>Regression</subject><subject>Training</subject><issn>0013-5194</issn><issn>1350-911X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2000</creationdate><recordtype>article</recordtype><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNpdkE1LAzEYhIMoWKv_IeDFy0K-3mRzlOIXVDzUg7fymg9J3e6uyW5_v8F66mkYeGYY5owsuATWWM4_zsmCMS4b4FZdkqtSdtUKa82CvG7GgN8hU_Q4TjiloS809bSMmEugU8bUp_6LepyQxiHTtB_zcAi-EsfgIeQUk_uLXpOLiF0JN_-6JJvHh_fVc7N-e3pZ3a-bUXPdSAArPTCQShkdrIiGG-NdkK0N3BuMQoHA2FpmhJQOvf_UClqwzGnj5JLcHVvrkp85lGm7T8WFrsM-DHPZcg1cCaaFrujtCbob5tzXbZUSoDToeswvqX9YAQ</recordid><startdate>20000217</startdate><enddate>20000217</enddate><creator>Ahn, Sungjoo</creator><creator>Ko, Hanseok</creator><general>John Wiley & Sons, Inc</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>L6V</scope><scope>M7S</scope><scope>P5Z</scope><scope>P62</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>7SP</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>L7M</scope></search><sort><creationdate>20000217</creationdate><title>Speaker adaptations in sparse training data for improved speaker verification</title><author>Ahn, Sungjoo ; Ko, Hanseok</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p616-35593d50534476e92f7177dce389e1d7af2452af8907233caddb6458590c67c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2000</creationdate><topic>Adaptation</topic><topic>Mathematical models</topic><topic>Modelling</topic><topic>Program verification (computers)</topic><topic>Regression</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ahn, Sungjoo</creatorcontrib><creatorcontrib>Ko, Hanseok</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Electronics letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ahn, Sungjoo</au><au>Ko, Hanseok</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Speaker adaptations in sparse training data for improved speaker verification</atitle><jtitle>Electronics letters</jtitle><date>2000-02-17</date><risdate>2000</risdate><volume>36</volume><issue>4</issue><spage>1</spage><epage>1</epage><pages>1-1</pages><issn>0013-5194</issn><eissn>1350-911X</eissn><coden>ELLEAK</coden><abstract>The over-training problem in speaker verification occurs when modelling a speaker with sparse training data. The authors propose to solve this problem by employing effective speaker adaptations, using a hybrid version of the maximum a posteriori and maximum likelihood linear regression methods. Experimental results show that the speaker verification system, using the proposed hybrid adaptation scheme, outperforms systems based on speaker models without adaptation by a factor of up to 5.</abstract><cop>Stevenage</cop><pub>John Wiley & Sons, Inc</pub><tpages>1</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0013-5194 |
| ispartof | Electronics letters, 2000-02, Vol.36 (4), p.1-1 |
| issn | 0013-5194 1350-911X |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1651420626 |
| source | Alma/SFX Local Collection |
| subjects | Adaptation Mathematical models Modelling Program verification (computers) Regression Training |
| title | Speaker adaptations in sparse training data for improved speaker verification |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T13%3A44%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Speaker%20adaptations%20in%20sparse%20training%20data%20for%20improved%20speaker%20verification&rft.jtitle=Electronics%20letters&rft.au=Ahn,%20Sungjoo&rft.date=2000-02-17&rft.volume=36&rft.issue=4&rft.spage=1&rft.epage=1&rft.pages=1-1&rft.issn=0013-5194&rft.eissn=1350-911X&rft.coden=ELLEAK&rft_id=info:doi/&rft_dat=%3Cproquest%3E1651420626%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1625465601&rft_id=info:pmid/&rfr_iscdi=true |