Loading…
Performance improvement of automatic speech recognition systems via multiple language models produced by sentence-based clustering
Grammar-based speech recognition systems exhibit performance degradation as their vocabulary sizes increase. Data clustering is deemed to reduce the proportionality of this problem. We introduce an approach to data clustering for automatic speech recognition systems using kohonen self-organized map....
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 367 |
| container_issue | |
| container_start_page | 362 |
| container_title | |
| container_volume | |
| creator | Sushil Kumar Podder Shaban, K. Sun, J. Karray, F. Basir, O. Kamel, M. |
| description | Grammar-based speech recognition systems exhibit performance degradation as their vocabulary sizes increase. Data clustering is deemed to reduce the proportionality of this problem. We introduce an approach to data clustering for automatic speech recognition systems using kohonen self-organized map. Clustering results are used further to build a language model for each of the clusters using CMU-Cambridge toolkit. The approach was implemented as a prototype for a large vocabulary and continuous speech recognition system and about 8% performance improvement was achieved in comparison with the performance achieved using the language model and dictionary provided by Sphinx3. We present the experimental results along with discussions, analysis and potential future directions. |
| doi_str_mv | 10.1109/NLPKE.2003.1275932 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1275932</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1275932</ieee_id><sourcerecordid>1275932</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-ee6af7c11e9266a7eafaf54f467e172e2611b9b7ca18c7a648f5c488815959b63</originalsourceid><addsrcrecordid>eNotkE1qwzAUhAWl0JLmAu1GF3AqyZZkLUtIf2hos2jX4Vl5clUs21hyINuevIJkGBiYxTcwhNxztuKcmceP7e59sxKMlSsutDSluCJLo2uWXWrDhLghyxh_WVZppFLylvztcHLDFKC3SH0Yp-GIAftEB0dhTkOA5C2NI6L9oRPaoe198kNP4ykmDJEePdAwd8mPHdIO-naGFmkYDthFmnGH2eKBNicaMxXzStFAzI3t5gyYfN_ekWsHXcTlJRfk-3nztX4ttp8vb-unbeG5lqlAVOC05RyNUAo0ggMnK1cpjVwLFIrzxjTaAq-tBlXVTtqqrmsujTSNKhfk4cz1iLgfJx9gOu0vT5X_1AVjBQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Performance improvement of automatic speech recognition systems via multiple language models produced by sentence-based clustering</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Sushil Kumar Podder ; Shaban, K. ; Sun, J. ; Karray, F. ; Basir, O. ; Kamel, M.</creator><creatorcontrib>Sushil Kumar Podder ; Shaban, K. ; Sun, J. ; Karray, F. ; Basir, O. ; Kamel, M.</creatorcontrib><description>Grammar-based speech recognition systems exhibit performance degradation as their vocabulary sizes increase. Data clustering is deemed to reduce the proportionality of this problem. We introduce an approach to data clustering for automatic speech recognition systems using kohonen self-organized map. Clustering results are used further to build a language model for each of the clusters using CMU-Cambridge toolkit. The approach was implemented as a prototype for a large vocabulary and continuous speech recognition system and about 8% performance improvement was achieved in comparison with the performance achieved using the language model and dictionary provided by Sphinx3. We present the experimental results along with discussions, analysis and potential future directions.</description><identifier>ISBN: 9780780379022</identifier><identifier>ISBN: 0780379020</identifier><identifier>DOI: 10.1109/NLPKE.2003.1275932</identifier><language>eng</language><publisher>IEEE</publisher><subject>Automatic speech recognition ; Degradation ; Dictionaries ; Engines ; Natural languages ; Performance analysis ; Speech analysis ; Speech recognition ; Sun ; Vocabulary</subject><ispartof>International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003, 2003, p.362-367</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/1275932$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1275932$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Sushil Kumar Podder</creatorcontrib><creatorcontrib>Shaban, K.</creatorcontrib><creatorcontrib>Sun, J.</creatorcontrib><creatorcontrib>Karray, F.</creatorcontrib><creatorcontrib>Basir, O.</creatorcontrib><creatorcontrib>Kamel, M.</creatorcontrib><title>Performance improvement of automatic speech recognition systems via multiple language models produced by sentence-based clustering</title><title>International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003</title><addtitle>NLPKE</addtitle><description>Grammar-based speech recognition systems exhibit performance degradation as their vocabulary sizes increase. Data clustering is deemed to reduce the proportionality of this problem. We introduce an approach to data clustering for automatic speech recognition systems using kohonen self-organized map. Clustering results are used further to build a language model for each of the clusters using CMU-Cambridge toolkit. The approach was implemented as a prototype for a large vocabulary and continuous speech recognition system and about 8% performance improvement was achieved in comparison with the performance achieved using the language model and dictionary provided by Sphinx3. We present the experimental results along with discussions, analysis and potential future directions.</description><subject>Automatic speech recognition</subject><subject>Degradation</subject><subject>Dictionaries</subject><subject>Engines</subject><subject>Natural languages</subject><subject>Performance analysis</subject><subject>Speech analysis</subject><subject>Speech recognition</subject><subject>Sun</subject><subject>Vocabulary</subject><isbn>9780780379022</isbn><isbn>0780379020</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2003</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotkE1qwzAUhAWl0JLmAu1GF3AqyZZkLUtIf2hos2jX4Vl5clUs21hyINuevIJkGBiYxTcwhNxztuKcmceP7e59sxKMlSsutDSluCJLo2uWXWrDhLghyxh_WVZppFLylvztcHLDFKC3SH0Yp-GIAftEB0dhTkOA5C2NI6L9oRPaoe198kNP4ykmDJEePdAwd8mPHdIO-naGFmkYDthFmnGH2eKBNicaMxXzStFAzI3t5gyYfN_ekWsHXcTlJRfk-3nztX4ttp8vb-unbeG5lqlAVOC05RyNUAo0ggMnK1cpjVwLFIrzxjTaAq-tBlXVTtqqrmsujTSNKhfk4cz1iLgfJx9gOu0vT5X_1AVjBQ</recordid><startdate>2003</startdate><enddate>2003</enddate><creator>Sushil Kumar Podder</creator><creator>Shaban, K.</creator><creator>Sun, J.</creator><creator>Karray, F.</creator><creator>Basir, O.</creator><creator>Kamel, M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>2003</creationdate><title>Performance improvement of automatic speech recognition systems via multiple language models produced by sentence-based clustering</title><author>Sushil Kumar Podder ; Shaban, K. ; Sun, J. ; Karray, F. ; Basir, O. ; Kamel, M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-ee6af7c11e9266a7eafaf54f467e172e2611b9b7ca18c7a648f5c488815959b63</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2003</creationdate><topic>Automatic speech recognition</topic><topic>Degradation</topic><topic>Dictionaries</topic><topic>Engines</topic><topic>Natural languages</topic><topic>Performance analysis</topic><topic>Speech analysis</topic><topic>Speech recognition</topic><topic>Sun</topic><topic>Vocabulary</topic><toplevel>online_resources</toplevel><creatorcontrib>Sushil Kumar Podder</creatorcontrib><creatorcontrib>Shaban, K.</creatorcontrib><creatorcontrib>Sun, J.</creatorcontrib><creatorcontrib>Karray, F.</creatorcontrib><creatorcontrib>Basir, O.</creatorcontrib><creatorcontrib>Kamel, M.</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 Xplore</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>Sushil Kumar Podder</au><au>Shaban, K.</au><au>Sun, J.</au><au>Karray, F.</au><au>Basir, O.</au><au>Kamel, M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Performance improvement of automatic speech recognition systems via multiple language models produced by sentence-based clustering</atitle><btitle>International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003</btitle><stitle>NLPKE</stitle><date>2003</date><risdate>2003</risdate><spage>362</spage><epage>367</epage><pages>362-367</pages><isbn>9780780379022</isbn><isbn>0780379020</isbn><abstract>Grammar-based speech recognition systems exhibit performance degradation as their vocabulary sizes increase. Data clustering is deemed to reduce the proportionality of this problem. We introduce an approach to data clustering for automatic speech recognition systems using kohonen self-organized map. Clustering results are used further to build a language model for each of the clusters using CMU-Cambridge toolkit. The approach was implemented as a prototype for a large vocabulary and continuous speech recognition system and about 8% performance improvement was achieved in comparison with the performance achieved using the language model and dictionary provided by Sphinx3. We present the experimental results along with discussions, analysis and potential future directions.</abstract><pub>IEEE</pub><doi>10.1109/NLPKE.2003.1275932</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 9780780379022 |
| ispartof | International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003, 2003, p.362-367 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_1275932 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Automatic speech recognition Degradation Dictionaries Engines Natural languages Performance analysis Speech analysis Speech recognition Sun Vocabulary |
| title | Performance improvement of automatic speech recognition systems via multiple language models produced by sentence-based clustering |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T22%3A04%3A49IST&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=Performance%20improvement%20of%20automatic%20speech%20recognition%20systems%20via%20multiple%20language%20models%20produced%20by%20sentence-based%20clustering&rft.btitle=International%20Conference%20on%20Natural%20Language%20Processing%20and%20Knowledge%20Engineering,%202003.%20Proceedings.%202003&rft.au=Sushil%20Kumar%20Podder&rft.date=2003&rft.spage=362&rft.epage=367&rft.pages=362-367&rft.isbn=9780780379022&rft.isbn_list=0780379020&rft_id=info:doi/10.1109/NLPKE.2003.1275932&rft_dat=%3Cieee_6IE%3E1275932%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-ee6af7c11e9266a7eafaf54f467e172e2611b9b7ca18c7a648f5c488815959b63%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=1275932&rfr_iscdi=true |