Genetic algorithm on speech recognition by using DHMM
This paper uses genetic algorithms to train a codebook for the modeling of Discrete Hidden Markov Model (DHMM) applied to speech recognition. The GA-trained DHMM is then used to increase the recognition rate for Mandarin speeches. Vector quantization based on a codebook is a fundamental process to r...
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 | 1338 |
|---|---|
| container_issue | |
| container_start_page | 1333 |
| container_title | |
| container_volume | |
| creator | Shing-Tai Pan Ching-Fa Chen Yi-Heng Tsai |
| description | This paper uses genetic algorithms to train a codebook for the modeling of Discrete Hidden Markov Model (DHMM) applied to speech recognition. The GA-trained DHMM is then used to increase the recognition rate for Mandarin speeches. Vector quantization based on a codebook is a fundamental process to recognize the speech signal by DHMM. A codebook will be first trained by genetic algorithms through Mandarin speech features. The speech features are then quantized based on the trained codebook. Subsequently, the quantized speech features are statistically used to train the model of DHMM for speech recognition. All the speech features to be recognized should go through the codebook before being fed into the DHMM model for recognition. Experimental results show that the speech recognition rate can be improved by using genetic algorithms to train the model of DHMM. |
| doi_str_mv | 10.1109/ICIEA.2012.6360929 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6360929</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6360929</ieee_id><sourcerecordid>6360929</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-889e0ec5577e90c5a9dac3f8407b40cb6a724831a195c01e9b254b28e63013643</originalsourceid><addsrcrecordid>eNo1kM1OwkAUhce_RMS-gG76Aq1z5_8uSUVoAnHDwh2ZjpcyBlrS1gVvb6N4Nic5X3Jychh7Ap4DcHwpi3I-ywUHkRtpOAq8YglaB0pbKwAQr9lEgHaZEGhv2MM_cB-3v8BkQoK7Z0nff_FRDpx0ZsL0ghoaYkj9oW67OOyPaduk_Yko7NOOQls3cYhjVJ3T7z42dfq6XK8f2d3OH3pKLj5lm7f5plhmq_dFWcxWWUQ-ZM4hcQp6XELIg_b46YPcOcVtpXiojLdCOQkeUAcOhJXQqhKOjOQgjZJT9vxXG4loe-ri0Xfn7eUA-QPqFkjo</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Genetic algorithm on speech recognition by using DHMM</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Shing-Tai Pan ; Ching-Fa Chen ; Yi-Heng Tsai</creator><creatorcontrib>Shing-Tai Pan ; Ching-Fa Chen ; Yi-Heng Tsai</creatorcontrib><description>This paper uses genetic algorithms to train a codebook for the modeling of Discrete Hidden Markov Model (DHMM) applied to speech recognition. The GA-trained DHMM is then used to increase the recognition rate for Mandarin speeches. Vector quantization based on a codebook is a fundamental process to recognize the speech signal by DHMM. A codebook will be first trained by genetic algorithms through Mandarin speech features. The speech features are then quantized based on the trained codebook. Subsequently, the quantized speech features are statistically used to train the model of DHMM for speech recognition. All the speech features to be recognized should go through the codebook before being fed into the DHMM model for recognition. Experimental results show that the speech recognition rate can be improved by using genetic algorithms to train the model of DHMM.</description><identifier>ISSN: 2156-2318</identifier><identifier>ISBN: 145772118X</identifier><identifier>ISBN: 9781457721182</identifier><identifier>EISSN: 2158-2297</identifier><identifier>EISBN: 9781457721199</identifier><identifier>EISBN: 9781457721175</identifier><identifier>EISBN: 1457721198</identifier><identifier>EISBN: 1457721171</identifier><identifier>DOI: 10.1109/ICIEA.2012.6360929</identifier><language>eng</language><publisher>IEEE</publisher><subject>Biological cells ; codebook ; Discrete Hidden Markov Model ; genetic algorithm ; Hidden Markov models ; Speech ; Speech coding ; Speech recognition ; Support vector machine classification ; Training</subject><ispartof>2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA), 2012, p.1333-1338</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/6360929$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2051,27904,54899</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6360929$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Shing-Tai Pan</creatorcontrib><creatorcontrib>Ching-Fa Chen</creatorcontrib><creatorcontrib>Yi-Heng Tsai</creatorcontrib><title>Genetic algorithm on speech recognition by using DHMM</title><title>2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA)</title><addtitle>ICIEA</addtitle><description>This paper uses genetic algorithms to train a codebook for the modeling of Discrete Hidden Markov Model (DHMM) applied to speech recognition. The GA-trained DHMM is then used to increase the recognition rate for Mandarin speeches. Vector quantization based on a codebook is a fundamental process to recognize the speech signal by DHMM. A codebook will be first trained by genetic algorithms through Mandarin speech features. The speech features are then quantized based on the trained codebook. Subsequently, the quantized speech features are statistically used to train the model of DHMM for speech recognition. All the speech features to be recognized should go through the codebook before being fed into the DHMM model for recognition. Experimental results show that the speech recognition rate can be improved by using genetic algorithms to train the model of DHMM.</description><subject>Biological cells</subject><subject>codebook</subject><subject>Discrete Hidden Markov Model</subject><subject>genetic algorithm</subject><subject>Hidden Markov models</subject><subject>Speech</subject><subject>Speech coding</subject><subject>Speech recognition</subject><subject>Support vector machine classification</subject><subject>Training</subject><issn>2156-2318</issn><issn>2158-2297</issn><isbn>145772118X</isbn><isbn>9781457721182</isbn><isbn>9781457721199</isbn><isbn>9781457721175</isbn><isbn>1457721198</isbn><isbn>1457721171</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1kM1OwkAUhce_RMS-gG76Aq1z5_8uSUVoAnHDwh2ZjpcyBlrS1gVvb6N4Nic5X3Jychh7Ap4DcHwpi3I-ywUHkRtpOAq8YglaB0pbKwAQr9lEgHaZEGhv2MM_cB-3v8BkQoK7Z0nff_FRDpx0ZsL0ghoaYkj9oW67OOyPaduk_Yko7NOOQls3cYhjVJ3T7z42dfq6XK8f2d3OH3pKLj5lm7f5plhmq_dFWcxWWUQ-ZM4hcQp6XELIg_b46YPcOcVtpXiojLdCOQkeUAcOhJXQqhKOjOQgjZJT9vxXG4loe-ri0Xfn7eUA-QPqFkjo</recordid><startdate>201207</startdate><enddate>201207</enddate><creator>Shing-Tai Pan</creator><creator>Ching-Fa Chen</creator><creator>Yi-Heng Tsai</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201207</creationdate><title>Genetic algorithm on speech recognition by using DHMM</title><author>Shing-Tai Pan ; Ching-Fa Chen ; Yi-Heng Tsai</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-889e0ec5577e90c5a9dac3f8407b40cb6a724831a195c01e9b254b28e63013643</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Biological cells</topic><topic>codebook</topic><topic>Discrete Hidden Markov Model</topic><topic>genetic algorithm</topic><topic>Hidden Markov models</topic><topic>Speech</topic><topic>Speech coding</topic><topic>Speech recognition</topic><topic>Support vector machine classification</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Shing-Tai Pan</creatorcontrib><creatorcontrib>Ching-Fa Chen</creatorcontrib><creatorcontrib>Yi-Heng Tsai</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>Shing-Tai Pan</au><au>Ching-Fa Chen</au><au>Yi-Heng Tsai</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Genetic algorithm on speech recognition by using DHMM</atitle><btitle>2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA)</btitle><stitle>ICIEA</stitle><date>2012-07</date><risdate>2012</risdate><spage>1333</spage><epage>1338</epage><pages>1333-1338</pages><issn>2156-2318</issn><eissn>2158-2297</eissn><isbn>145772118X</isbn><isbn>9781457721182</isbn><eisbn>9781457721199</eisbn><eisbn>9781457721175</eisbn><eisbn>1457721198</eisbn><eisbn>1457721171</eisbn><abstract>This paper uses genetic algorithms to train a codebook for the modeling of Discrete Hidden Markov Model (DHMM) applied to speech recognition. The GA-trained DHMM is then used to increase the recognition rate for Mandarin speeches. Vector quantization based on a codebook is a fundamental process to recognize the speech signal by DHMM. A codebook will be first trained by genetic algorithms through Mandarin speech features. The speech features are then quantized based on the trained codebook. Subsequently, the quantized speech features are statistically used to train the model of DHMM for speech recognition. All the speech features to be recognized should go through the codebook before being fed into the DHMM model for recognition. Experimental results show that the speech recognition rate can be improved by using genetic algorithms to train the model of DHMM.</abstract><pub>IEEE</pub><doi>10.1109/ICIEA.2012.6360929</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2156-2318 |
| ispartof | 2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA), 2012, p.1333-1338 |
| issn | 2156-2318 2158-2297 |
| language | eng |
| recordid | cdi_ieee_primary_6360929 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Biological cells codebook Discrete Hidden Markov Model genetic algorithm Hidden Markov models Speech Speech coding Speech recognition Support vector machine classification Training |
| title | Genetic algorithm on speech recognition by using DHMM |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T23%3A12%3A24IST&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=Genetic%20algorithm%20on%20speech%20recognition%20by%20using%20DHMM&rft.btitle=2012%207th%20IEEE%20Conference%20on%20Industrial%20Electronics%20and%20Applications%20(ICIEA)&rft.au=Shing-Tai%20Pan&rft.date=2012-07&rft.spage=1333&rft.epage=1338&rft.pages=1333-1338&rft.issn=2156-2318&rft.eissn=2158-2297&rft.isbn=145772118X&rft.isbn_list=9781457721182&rft_id=info:doi/10.1109/ICIEA.2012.6360929&rft_dat=%3Cieee_6IE%3E6360929%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781457721199&rft.eisbn_list=9781457721175&rft.eisbn_list=1457721198&rft.eisbn_list=1457721171&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6360929&rfr_iscdi=true |