Boosting Gaussian mixtures in an LVCSR system
In this paper, we apply boosting to the problem of frame-level phone classification, and use the resulting system to perform voicemail transcription. We develop parallel, hierarchical, and restricted versions of the classic AdaBoost algorithm, which enable the technique to be used in large-scale spe...
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 | 1530 vol.3 |
|---|---|
| container_issue | |
| container_start_page | 1527 |
| container_title | |
| container_volume | 3 |
| creator | Zweig, G. Padmanabhan, M. |
| description | In this paper, we apply boosting to the problem of frame-level phone classification, and use the resulting system to perform voicemail transcription. We develop parallel, hierarchical, and restricted versions of the classic AdaBoost algorithm, which enable the technique to be used in large-scale speech recognition tasks with hundreds of thousands of Gaussians and tens of millions of training frames. We report small but consistent improvements in both frame recognition accuracy and word error rate. |
| doi_str_mv | 10.1109/ICASSP.2000.861945 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_861945</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>861945</ieee_id><sourcerecordid>861945</sourcerecordid><originalsourceid>FETCH-LOGICAL-i172t-6fc75da3016f9a133b4dcfa2a8f6b3b3bb93e6c636b3fca719aea421f40851f13</originalsourceid><addsrcrecordid>eNotT9tKxDAUDF7Auu4P7FN-IDUnSXN51KKrUFCsim_LaTeRiO1K0wX37w2szMAwDzPMELICXgJwd_1Y37Ttcyk456XV4FR1QgohjWPg-McpWTpjeabUwklxRgqoBGcalLsglyl95Zw1yhaE3e52aY7jJ13jPqWIIx3i77yffKJxpNk273X7QtMhzX64IucBv5Nf_uuCvN3fvdYPrHla50kNi2DEzHToTbVFyUEHhyBlp7Z9QIE26E5mdE563WuZXejRgEOPSkBQ3FYQQC7I6tgbvfebnykOOB02x6PyD8-cRN0</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Boosting Gaussian mixtures in an LVCSR system</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Zweig, G. ; Padmanabhan, M.</creator><creatorcontrib>Zweig, G. ; Padmanabhan, M.</creatorcontrib><description>In this paper, we apply boosting to the problem of frame-level phone classification, and use the resulting system to perform voicemail transcription. We develop parallel, hierarchical, and restricted versions of the classic AdaBoost algorithm, which enable the technique to be used in large-scale speech recognition tasks with hundreds of thousands of Gaussians and tens of millions of training frames. We report small but consistent improvements in both frame recognition accuracy and word error rate.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9780780362932</identifier><identifier>ISBN: 0780362934</identifier><identifier>EISSN: 2379-190X</identifier><identifier>DOI: 10.1109/ICASSP.2000.861945</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acoustic applications ; Acoustic testing ; Boosting ; Error analysis ; Large-scale systems ; Neural networks ; Probability distribution ; Speech recognition ; System testing ; Voice mail</subject><ispartof>2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100), 2000, Vol.3, p.1527-1530 vol.3</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/861945$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/861945$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Zweig, G.</creatorcontrib><creatorcontrib>Padmanabhan, M.</creatorcontrib><title>Boosting Gaussian mixtures in an LVCSR system</title><title>2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)</title><addtitle>ICASSP</addtitle><description>In this paper, we apply boosting to the problem of frame-level phone classification, and use the resulting system to perform voicemail transcription. We develop parallel, hierarchical, and restricted versions of the classic AdaBoost algorithm, which enable the technique to be used in large-scale speech recognition tasks with hundreds of thousands of Gaussians and tens of millions of training frames. We report small but consistent improvements in both frame recognition accuracy and word error rate.</description><subject>Acoustic applications</subject><subject>Acoustic testing</subject><subject>Boosting</subject><subject>Error analysis</subject><subject>Large-scale systems</subject><subject>Neural networks</subject><subject>Probability distribution</subject><subject>Speech recognition</subject><subject>System testing</subject><subject>Voice mail</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9780780362932</isbn><isbn>0780362934</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2000</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotT9tKxDAUDF7Auu4P7FN-IDUnSXN51KKrUFCsim_LaTeRiO1K0wX37w2szMAwDzPMELICXgJwd_1Y37Ttcyk456XV4FR1QgohjWPg-McpWTpjeabUwklxRgqoBGcalLsglyl95Zw1yhaE3e52aY7jJ13jPqWIIx3i77yffKJxpNk273X7QtMhzX64IucBv5Nf_uuCvN3fvdYPrHla50kNi2DEzHToTbVFyUEHhyBlp7Z9QIE26E5mdE563WuZXejRgEOPSkBQ3FYQQC7I6tgbvfebnykOOB02x6PyD8-cRN0</recordid><startdate>2000</startdate><enddate>2000</enddate><creator>Zweig, G.</creator><creator>Padmanabhan, M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>2000</creationdate><title>Boosting Gaussian mixtures in an LVCSR system</title><author>Zweig, G. ; Padmanabhan, M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i172t-6fc75da3016f9a133b4dcfa2a8f6b3b3bb93e6c636b3fca719aea421f40851f13</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2000</creationdate><topic>Acoustic applications</topic><topic>Acoustic testing</topic><topic>Boosting</topic><topic>Error analysis</topic><topic>Large-scale systems</topic><topic>Neural networks</topic><topic>Probability distribution</topic><topic>Speech recognition</topic><topic>System testing</topic><topic>Voice mail</topic><toplevel>online_resources</toplevel><creatorcontrib>Zweig, G.</creatorcontrib><creatorcontrib>Padmanabhan, M.</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>Zweig, G.</au><au>Padmanabhan, M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Boosting Gaussian mixtures in an LVCSR system</atitle><btitle>2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)</btitle><stitle>ICASSP</stitle><date>2000</date><risdate>2000</risdate><volume>3</volume><spage>1527</spage><epage>1530 vol.3</epage><pages>1527-1530 vol.3</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>9780780362932</isbn><isbn>0780362934</isbn><abstract>In this paper, we apply boosting to the problem of frame-level phone classification, and use the resulting system to perform voicemail transcription. We develop parallel, hierarchical, and restricted versions of the classic AdaBoost algorithm, which enable the technique to be used in large-scale speech recognition tasks with hundreds of thousands of Gaussians and tens of millions of training frames. We report small but consistent improvements in both frame recognition accuracy and word error rate.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2000.861945</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-6149 |
| ispartof | 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100), 2000, Vol.3, p.1527-1530 vol.3 |
| issn | 1520-6149 2379-190X |
| language | eng |
| recordid | cdi_ieee_primary_861945 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Acoustic applications Acoustic testing Boosting Error analysis Large-scale systems Neural networks Probability distribution Speech recognition System testing Voice mail |
| title | Boosting Gaussian mixtures in an LVCSR system |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-21T12%3A17%3A45IST&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=Boosting%20Gaussian%20mixtures%20in%20an%20LVCSR%20system&rft.btitle=2000%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech,%20and%20Signal%20Processing.%20Proceedings%20(Cat.%20No.00CH37100)&rft.au=Zweig,%20G.&rft.date=2000&rft.volume=3&rft.spage=1527&rft.epage=1530%20vol.3&rft.pages=1527-1530%20vol.3&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=9780780362932&rft.isbn_list=0780362934&rft_id=info:doi/10.1109/ICASSP.2000.861945&rft_dat=%3Cieee_6IE%3E861945%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=861945&rfr_iscdi=true |