Model adaptation based on improved variance estimation for robust speech recognition
This paper proposes a model adaptation algorithm based on improved variance estimation for noise robust speech recognition. In this algorithm, the approximate closed-form variance estimation is extended from the feature space to the model space and the dynamic parameters of the hidden Markov model (...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 4 |
|---|---|
| container_issue | |
| container_start_page | 1 |
| container_title | |
| container_volume | |
| creator | Yong Lu Zongyu Xu Qin Yan Lin Zhou |
| description | This paper proposes a model adaptation algorithm based on improved variance estimation for noise robust speech recognition. In this algorithm, the approximate closed-form variance estimation is extended from the feature space to the model space and the dynamic parameters of the hidden Markov model (HMM) as well as the static parameters are converted to testing conditions. The experimental results show that the proposed model adaptation algorithm can converge quickly and outperforms the feature compensation method using the approximate closed-form variance estimation. |
| doi_str_mv | 10.1109/WCSP.2012.6542942 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6542942</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6542942</ieee_id><sourcerecordid>6542942</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-129ff949b2424b8a979daa33a85c1962b2369560fd45964943638987e0c9c53c3</originalsourceid><addsrcrecordid>eNotUF1LwzAUjYigzv4A8SV_YPXmu_dRijphouDEx5GmqUa2piR14L-3sj6dczkfXA4h1wxKxgBvP-q315ID46VWkqPkJ-SSSW2EqjjCKSnQVPMtAM9JkfM3AExZwwAuyOY5tn5HbWuH0Y4h9rSx2bd0ImE_pHiY-MGmYHvnqc9j2B9dXUw0xeYnjzQP3rsvmryLn334V6_IWWd32RczLsj7w_2mXi3XL49P9d16GZhR45Jx7DqU2HDJZVNZNNhaK4StlGOoecOFRqWha6VCLVEKLSqsjAeHTgknFuTm2Bu899shTc-l3-08hPgDIQFRYg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Model adaptation based on improved variance estimation for robust speech recognition</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Yong Lu ; Zongyu Xu ; Qin Yan ; Lin Zhou</creator><creatorcontrib>Yong Lu ; Zongyu Xu ; Qin Yan ; Lin Zhou</creatorcontrib><description>This paper proposes a model adaptation algorithm based on improved variance estimation for noise robust speech recognition. In this algorithm, the approximate closed-form variance estimation is extended from the feature space to the model space and the dynamic parameters of the hidden Markov model (HMM) as well as the static parameters are converted to testing conditions. The experimental results show that the proposed model adaptation algorithm can converge quickly and outperforms the feature compensation method using the approximate closed-form variance estimation.</description><identifier>ISBN: 9781467358309</identifier><identifier>ISBN: 1467358304</identifier><identifier>EISBN: 1467358290</identifier><identifier>EISBN: 9781467358293</identifier><identifier>EISBN: 9781467358316</identifier><identifier>EISBN: 1467358312</identifier><identifier>DOI: 10.1109/WCSP.2012.6542942</identifier><language>eng</language><publisher>IEEE</publisher><subject>model adaptation ; speech recognition ; variance estimation ; vector Taylor series</subject><ispartof>2012 International Conference on Wireless Communications and Signal Processing (WCSP), 2012, p.1-4</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/6542942$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6542942$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yong Lu</creatorcontrib><creatorcontrib>Zongyu Xu</creatorcontrib><creatorcontrib>Qin Yan</creatorcontrib><creatorcontrib>Lin Zhou</creatorcontrib><title>Model adaptation based on improved variance estimation for robust speech recognition</title><title>2012 International Conference on Wireless Communications and Signal Processing (WCSP)</title><addtitle>WCSP</addtitle><description>This paper proposes a model adaptation algorithm based on improved variance estimation for noise robust speech recognition. In this algorithm, the approximate closed-form variance estimation is extended from the feature space to the model space and the dynamic parameters of the hidden Markov model (HMM) as well as the static parameters are converted to testing conditions. The experimental results show that the proposed model adaptation algorithm can converge quickly and outperforms the feature compensation method using the approximate closed-form variance estimation.</description><subject>model adaptation</subject><subject>speech recognition</subject><subject>variance estimation</subject><subject>vector Taylor series</subject><isbn>9781467358309</isbn><isbn>1467358304</isbn><isbn>1467358290</isbn><isbn>9781467358293</isbn><isbn>9781467358316</isbn><isbn>1467358312</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotUF1LwzAUjYigzv4A8SV_YPXmu_dRijphouDEx5GmqUa2piR14L-3sj6dczkfXA4h1wxKxgBvP-q315ID46VWkqPkJ-SSSW2EqjjCKSnQVPMtAM9JkfM3AExZwwAuyOY5tn5HbWuH0Y4h9rSx2bd0ImE_pHiY-MGmYHvnqc9j2B9dXUw0xeYnjzQP3rsvmryLn334V6_IWWd32RczLsj7w_2mXi3XL49P9d16GZhR45Jx7DqU2HDJZVNZNNhaK4StlGOoecOFRqWha6VCLVEKLSqsjAeHTgknFuTm2Bu899shTc-l3-08hPgDIQFRYg</recordid><startdate>201210</startdate><enddate>201210</enddate><creator>Yong Lu</creator><creator>Zongyu Xu</creator><creator>Qin Yan</creator><creator>Lin Zhou</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201210</creationdate><title>Model adaptation based on improved variance estimation for robust speech recognition</title><author>Yong Lu ; Zongyu Xu ; Qin Yan ; Lin Zhou</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-129ff949b2424b8a979daa33a85c1962b2369560fd45964943638987e0c9c53c3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>model adaptation</topic><topic>speech recognition</topic><topic>variance estimation</topic><topic>vector Taylor series</topic><toplevel>online_resources</toplevel><creatorcontrib>Yong Lu</creatorcontrib><creatorcontrib>Zongyu Xu</creatorcontrib><creatorcontrib>Qin Yan</creatorcontrib><creatorcontrib>Lin Zhou</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 (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>Yong Lu</au><au>Zongyu Xu</au><au>Qin Yan</au><au>Lin Zhou</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Model adaptation based on improved variance estimation for robust speech recognition</atitle><btitle>2012 International Conference on Wireless Communications and Signal Processing (WCSP)</btitle><stitle>WCSP</stitle><date>2012-10</date><risdate>2012</risdate><spage>1</spage><epage>4</epage><pages>1-4</pages><isbn>9781467358309</isbn><isbn>1467358304</isbn><eisbn>1467358290</eisbn><eisbn>9781467358293</eisbn><eisbn>9781467358316</eisbn><eisbn>1467358312</eisbn><abstract>This paper proposes a model adaptation algorithm based on improved variance estimation for noise robust speech recognition. In this algorithm, the approximate closed-form variance estimation is extended from the feature space to the model space and the dynamic parameters of the hidden Markov model (HMM) as well as the static parameters are converted to testing conditions. The experimental results show that the proposed model adaptation algorithm can converge quickly and outperforms the feature compensation method using the approximate closed-form variance estimation.</abstract><pub>IEEE</pub><doi>10.1109/WCSP.2012.6542942</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 9781467358309 |
| ispartof | 2012 International Conference on Wireless Communications and Signal Processing (WCSP), 2012, p.1-4 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_6542942 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | model adaptation speech recognition variance estimation vector Taylor series |
| title | Model adaptation based on improved variance estimation for robust speech recognition |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T09%3A37%3A46IST&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=Model%20adaptation%20based%20on%20improved%20variance%20estimation%20for%20robust%20speech%20recognition&rft.btitle=2012%20International%20Conference%20on%20Wireless%20Communications%20and%20Signal%20Processing%20(WCSP)&rft.au=Yong%20Lu&rft.date=2012-10&rft.spage=1&rft.epage=4&rft.pages=1-4&rft.isbn=9781467358309&rft.isbn_list=1467358304&rft_id=info:doi/10.1109/WCSP.2012.6542942&rft_dat=%3Cieee_6IE%3E6542942%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1467358290&rft.eisbn_list=9781467358293&rft.eisbn_list=9781467358316&rft.eisbn_list=1467358312&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6542942&rfr_iscdi=true |