Subspace Gaussian Mixture Models for speech recognition
We describe an acoustic modeling approach in which all phonetic states share a common Gaussian Mixture Model structure, and the means and mixture weights vary in a subspace of the total parameter space. We call this a Subspace Gaussian Mixture Model (SGMM). Globally shared parameters define the subs...
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 | 4333 |
|---|---|
| container_issue | |
| container_start_page | 4330 |
| container_title | |
| container_volume | |
| creator | Povey, Daniel Burget, Lukáš Agarwal, Mohit Akyazi, Pinar Kai Feng Ghoshal, Arnab Glembek, Ondřej Goel, Nagendra Kumar Karafiát, Martin Rastrow, Ariya Rose, Richard C Schwarz, Petr Thomas, Samuel |
| description | We describe an acoustic modeling approach in which all phonetic states share a common Gaussian Mixture Model structure, and the means and mixture weights vary in a subspace of the total parameter space. We call this a Subspace Gaussian Mixture Model (SGMM). Globally shared parameters define the subspace. This style of acoustic model allows for a much more compact representation and gives better results than a conventional modeling approach, particularly with smaller amounts of training data. |
| doi_str_mv | 10.1109/ICASSP.2010.5495662 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5495662</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5495662</ieee_id><sourcerecordid>5495662</sourcerecordid><originalsourceid>FETCH-LOGICAL-c291t-a6aee211d9c42647f8d1755cf3cf77de02e4ec78b4c73d2534707b83a5b3a3113</originalsourceid><addsrcrecordid>eNpVj81Kw0AUhUdUsNY-QTfzAqlzZ-78LaVoFVoUousymdzoSE1CJgF9ewt24-pwvsXhO4wtQawAhL99Wt-V5ctKiiPQ6LUx8owtvHWAEhGlN-b8X9f-gs1AS1EYQH_FrnP-FEI4i27GbDlVuQ-R-CZMOafQ8l36HqeB-K6r6ZB50w0890Txgw8Uu_c2jalrb9hlEw6ZFqecs7eH-9f1Y7F93hwNt0WUHsYimEAkAWofURq0javBah0bFRtraxKSkKJ1FUaraqkVWmErp4KuVFAAas6Wf7uJiPb9kL7C8LM__Va_mzNJsA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Subspace Gaussian Mixture Models for speech recognition</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Povey, Daniel ; Burget, Lukáš ; Agarwal, Mohit ; Akyazi, Pinar ; Kai Feng ; Ghoshal, Arnab ; Glembek, Ondřej ; Goel, Nagendra Kumar ; Karafiát, Martin ; Rastrow, Ariya ; Rose, Richard C ; Schwarz, Petr ; Thomas, Samuel</creator><creatorcontrib>Povey, Daniel ; Burget, Lukáš ; Agarwal, Mohit ; Akyazi, Pinar ; Kai Feng ; Ghoshal, Arnab ; Glembek, Ondřej ; Goel, Nagendra Kumar ; Karafiát, Martin ; Rastrow, Ariya ; Rose, Richard C ; Schwarz, Petr ; Thomas, Samuel</creatorcontrib><description>We describe an acoustic modeling approach in which all phonetic states share a common Gaussian Mixture Model structure, and the means and mixture weights vary in a subspace of the total parameter space. We call this a Subspace Gaussian Mixture Model (SGMM). Globally shared parameters define the subspace. This style of acoustic model allows for a much more compact representation and gives better results than a conventional modeling approach, particularly with smaller amounts of training data.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9781424442959</identifier><identifier>ISBN: 1424442958</identifier><identifier>EISBN: 9781424442966</identifier><identifier>EISBN: 1424442966</identifier><identifier>DOI: 10.1109/ICASSP.2010.5495662</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acoustic testing ; Costs ; Equations ; Gaussian Mixture Models ; Hidden Markov models ; Loudspeakers ; Natural languages ; Software testing ; Software tools ; Speech recognition ; Training data</subject><ispartof>2010 IEEE International Conference on Acoustics, Speech and Signal Processing, 2010, p.4330-4333</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c291t-a6aee211d9c42647f8d1755cf3cf77de02e4ec78b4c73d2534707b83a5b3a3113</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5495662$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5495662$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Povey, Daniel</creatorcontrib><creatorcontrib>Burget, Lukáš</creatorcontrib><creatorcontrib>Agarwal, Mohit</creatorcontrib><creatorcontrib>Akyazi, Pinar</creatorcontrib><creatorcontrib>Kai Feng</creatorcontrib><creatorcontrib>Ghoshal, Arnab</creatorcontrib><creatorcontrib>Glembek, Ondřej</creatorcontrib><creatorcontrib>Goel, Nagendra Kumar</creatorcontrib><creatorcontrib>Karafiát, Martin</creatorcontrib><creatorcontrib>Rastrow, Ariya</creatorcontrib><creatorcontrib>Rose, Richard C</creatorcontrib><creatorcontrib>Schwarz, Petr</creatorcontrib><creatorcontrib>Thomas, Samuel</creatorcontrib><title>Subspace Gaussian Mixture Models for speech recognition</title><title>2010 IEEE International Conference on Acoustics, Speech and Signal Processing</title><addtitle>ICASSP</addtitle><description>We describe an acoustic modeling approach in which all phonetic states share a common Gaussian Mixture Model structure, and the means and mixture weights vary in a subspace of the total parameter space. We call this a Subspace Gaussian Mixture Model (SGMM). Globally shared parameters define the subspace. This style of acoustic model allows for a much more compact representation and gives better results than a conventional modeling approach, particularly with smaller amounts of training data.</description><subject>Acoustic testing</subject><subject>Costs</subject><subject>Equations</subject><subject>Gaussian Mixture Models</subject><subject>Hidden Markov models</subject><subject>Loudspeakers</subject><subject>Natural languages</subject><subject>Software testing</subject><subject>Software tools</subject><subject>Speech recognition</subject><subject>Training data</subject><issn>1520-6149</issn><isbn>9781424442959</isbn><isbn>1424442958</isbn><isbn>9781424442966</isbn><isbn>1424442966</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2010</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpVj81Kw0AUhUdUsNY-QTfzAqlzZ-78LaVoFVoUousymdzoSE1CJgF9ewt24-pwvsXhO4wtQawAhL99Wt-V5ctKiiPQ6LUx8owtvHWAEhGlN-b8X9f-gs1AS1EYQH_FrnP-FEI4i27GbDlVuQ-R-CZMOafQ8l36HqeB-K6r6ZB50w0890Txgw8Uu_c2jalrb9hlEw6ZFqecs7eH-9f1Y7F93hwNt0WUHsYimEAkAWofURq0javBah0bFRtraxKSkKJ1FUaraqkVWmErp4KuVFAAas6Wf7uJiPb9kL7C8LM__Va_mzNJsA</recordid><startdate>201003</startdate><enddate>201003</enddate><creator>Povey, Daniel</creator><creator>Burget, Lukáš</creator><creator>Agarwal, Mohit</creator><creator>Akyazi, Pinar</creator><creator>Kai Feng</creator><creator>Ghoshal, Arnab</creator><creator>Glembek, Ondřej</creator><creator>Goel, Nagendra Kumar</creator><creator>Karafiát, Martin</creator><creator>Rastrow, Ariya</creator><creator>Rose, Richard C</creator><creator>Schwarz, Petr</creator><creator>Thomas, Samuel</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201003</creationdate><title>Subspace Gaussian Mixture Models for speech recognition</title><author>Povey, Daniel ; Burget, Lukáš ; Agarwal, Mohit ; Akyazi, Pinar ; Kai Feng ; Ghoshal, Arnab ; Glembek, Ondřej ; Goel, Nagendra Kumar ; Karafiát, Martin ; Rastrow, Ariya ; Rose, Richard C ; Schwarz, Petr ; Thomas, Samuel</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c291t-a6aee211d9c42647f8d1755cf3cf77de02e4ec78b4c73d2534707b83a5b3a3113</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Acoustic testing</topic><topic>Costs</topic><topic>Equations</topic><topic>Gaussian Mixture Models</topic><topic>Hidden Markov models</topic><topic>Loudspeakers</topic><topic>Natural languages</topic><topic>Software testing</topic><topic>Software tools</topic><topic>Speech recognition</topic><topic>Training data</topic><toplevel>online_resources</toplevel><creatorcontrib>Povey, Daniel</creatorcontrib><creatorcontrib>Burget, Lukáš</creatorcontrib><creatorcontrib>Agarwal, Mohit</creatorcontrib><creatorcontrib>Akyazi, Pinar</creatorcontrib><creatorcontrib>Kai Feng</creatorcontrib><creatorcontrib>Ghoshal, Arnab</creatorcontrib><creatorcontrib>Glembek, Ondřej</creatorcontrib><creatorcontrib>Goel, Nagendra Kumar</creatorcontrib><creatorcontrib>Karafiát, Martin</creatorcontrib><creatorcontrib>Rastrow, Ariya</creatorcontrib><creatorcontrib>Rose, Richard C</creatorcontrib><creatorcontrib>Schwarz, Petr</creatorcontrib><creatorcontrib>Thomas, Samuel</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Povey, Daniel</au><au>Burget, Lukáš</au><au>Agarwal, Mohit</au><au>Akyazi, Pinar</au><au>Kai Feng</au><au>Ghoshal, Arnab</au><au>Glembek, Ondřej</au><au>Goel, Nagendra Kumar</au><au>Karafiát, Martin</au><au>Rastrow, Ariya</au><au>Rose, Richard C</au><au>Schwarz, Petr</au><au>Thomas, Samuel</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Subspace Gaussian Mixture Models for speech recognition</atitle><btitle>2010 IEEE International Conference on Acoustics, Speech and Signal Processing</btitle><stitle>ICASSP</stitle><date>2010-03</date><risdate>2010</risdate><spage>4330</spage><epage>4333</epage><pages>4330-4333</pages><issn>1520-6149</issn><isbn>9781424442959</isbn><isbn>1424442958</isbn><eisbn>9781424442966</eisbn><eisbn>1424442966</eisbn><abstract>We describe an acoustic modeling approach in which all phonetic states share a common Gaussian Mixture Model structure, and the means and mixture weights vary in a subspace of the total parameter space. We call this a Subspace Gaussian Mixture Model (SGMM). Globally shared parameters define the subspace. This style of acoustic model allows for a much more compact representation and gives better results than a conventional modeling approach, particularly with smaller amounts of training data.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2010.5495662</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-6149 |
| ispartof | 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, 2010, p.4330-4333 |
| issn | 1520-6149 |
| language | eng |
| recordid | cdi_ieee_primary_5495662 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Acoustic testing Costs Equations Gaussian Mixture Models Hidden Markov models Loudspeakers Natural languages Software testing Software tools Speech recognition Training data |
| title | Subspace Gaussian Mixture Models for speech recognition |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T17%3A32%3A48IST&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=Subspace%20Gaussian%20Mixture%20Models%20for%20speech%20recognition&rft.btitle=2010%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech%20and%20Signal%20Processing&rft.au=Povey,%20Daniel&rft.date=2010-03&rft.spage=4330&rft.epage=4333&rft.pages=4330-4333&rft.issn=1520-6149&rft.isbn=9781424442959&rft.isbn_list=1424442958&rft_id=info:doi/10.1109/ICASSP.2010.5495662&rft_dat=%3Cieee_6IE%3E5495662%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424442966&rft.eisbn_list=1424442966&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5495662&rfr_iscdi=true |