Discriminative training of tied mixture density HMMs for online handwritten digit recognition
This paper describes and evaluates the maximum mutual information criterion (MMI) for online unconstrained-style handwritten digit recognition based on hidden Markov models (HMMs). The study focuses on determining the best MMI optimization scheme and the HMM parameters that exhibit the most discrimi...
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 | 817 |
|---|---|
| container_issue | |
| container_start_page | II |
| container_title | |
| container_volume | 2 |
| creator | Nopsuwanchai, R. Biem, A. |
| description | This paper describes and evaluates the maximum mutual information criterion (MMI) for online unconstrained-style handwritten digit recognition based on hidden Markov models (HMMs). The study focuses on determining the best MMI optimization scheme and the HMM parameters that exhibit the most discriminative capabilities in the context of tied mixture density hidden Markov models (TDHMMs), where all HMM states share a pool of Gaussians. The experimental results show that the second-order optimization scheme is the most efficient and that although means and covariance matrix are shared by all models, they contribute the most to discrimination. |
| doi_str_mv | 10.1109/ICASSP.2003.1202492 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1202492</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1202492</ieee_id><sourcerecordid>1202492</sourcerecordid><originalsourceid>FETCH-ieee_primary_12024923</originalsourceid><addsrcrecordid>eNp9j8tOwzAQRS0eEgH6Bd3MDySM7ZDES1RAZVEJqV10gyqrmYRB7RjZ5tG_p4uuka50FmdxdJWaaqy0Rnf3MntYLl8rg2grbdDUzpypwtjWldrh-lxNXNvhcbZtGmsuVKHvDZaNrt2Vuk7pAxG7tu4K9fbIaRt5z-IzfxPk6FlYRggDZKYe9vybvyJBT5I4H2C-WCQYQoQgOxaCdy_9T-ScSaDnkTNE2oZROHOQW3U5-F2iyYk3avr8tJrNSyaizeex6-Nhc3pg_7d_Mi5Ixw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Discriminative training of tied mixture density HMMs for online handwritten digit recognition</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Nopsuwanchai, R. ; Biem, A.</creator><creatorcontrib>Nopsuwanchai, R. ; Biem, A.</creatorcontrib><description>This paper describes and evaluates the maximum mutual information criterion (MMI) for online unconstrained-style handwritten digit recognition based on hidden Markov models (HMMs). The study focuses on determining the best MMI optimization scheme and the HMM parameters that exhibit the most discriminative capabilities in the context of tied mixture density hidden Markov models (TDHMMs), where all HMM states share a pool of Gaussians. The experimental results show that the second-order optimization scheme is the most efficient and that although means and covariance matrix are shared by all models, they contribute the most to discrimination.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9780780376632</identifier><identifier>ISBN: 0780376633</identifier><identifier>EISSN: 2379-190X</identifier><identifier>DOI: 10.1109/ICASSP.2003.1202492</identifier><language>eng</language><publisher>IEEE</publisher><subject>Covariance matrix ; Handheld computers ; Handwriting recognition ; Hardware ; Hidden Markov models ; Laboratories ; Maximum likelihood estimation ; Mutual information ; Personal digital assistants ; Power system modeling</subject><ispartof>2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03), 2003, Vol.2, p.II-817</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/1202492$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2051,4035,4036,27904,54899</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1202492$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Nopsuwanchai, R.</creatorcontrib><creatorcontrib>Biem, A.</creatorcontrib><title>Discriminative training of tied mixture density HMMs for online handwritten digit recognition</title><title>2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)</title><addtitle>ICASSP</addtitle><description>This paper describes and evaluates the maximum mutual information criterion (MMI) for online unconstrained-style handwritten digit recognition based on hidden Markov models (HMMs). The study focuses on determining the best MMI optimization scheme and the HMM parameters that exhibit the most discriminative capabilities in the context of tied mixture density hidden Markov models (TDHMMs), where all HMM states share a pool of Gaussians. The experimental results show that the second-order optimization scheme is the most efficient and that although means and covariance matrix are shared by all models, they contribute the most to discrimination.</description><subject>Covariance matrix</subject><subject>Handheld computers</subject><subject>Handwriting recognition</subject><subject>Hardware</subject><subject>Hidden Markov models</subject><subject>Laboratories</subject><subject>Maximum likelihood estimation</subject><subject>Mutual information</subject><subject>Personal digital assistants</subject><subject>Power system modeling</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9780780376632</isbn><isbn>0780376633</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2003</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNp9j8tOwzAQRS0eEgH6Bd3MDySM7ZDES1RAZVEJqV10gyqrmYRB7RjZ5tG_p4uuka50FmdxdJWaaqy0Rnf3MntYLl8rg2grbdDUzpypwtjWldrh-lxNXNvhcbZtGmsuVKHvDZaNrt2Vuk7pAxG7tu4K9fbIaRt5z-IzfxPk6FlYRggDZKYe9vybvyJBT5I4H2C-WCQYQoQgOxaCdy_9T-ScSaDnkTNE2oZROHOQW3U5-F2iyYk3avr8tJrNSyaizeex6-Nhc3pg_7d_Mi5Ixw</recordid><startdate>2003</startdate><enddate>2003</enddate><creator>Nopsuwanchai, R.</creator><creator>Biem, A.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>2003</creationdate><title>Discriminative training of tied mixture density HMMs for online handwritten digit recognition</title><author>Nopsuwanchai, R. ; Biem, A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ieee_primary_12024923</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2003</creationdate><topic>Covariance matrix</topic><topic>Handheld computers</topic><topic>Handwriting recognition</topic><topic>Hardware</topic><topic>Hidden Markov models</topic><topic>Laboratories</topic><topic>Maximum likelihood estimation</topic><topic>Mutual information</topic><topic>Personal digital assistants</topic><topic>Power system modeling</topic><toplevel>online_resources</toplevel><creatorcontrib>Nopsuwanchai, R.</creatorcontrib><creatorcontrib>Biem, A.</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>Nopsuwanchai, R.</au><au>Biem, A.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Discriminative training of tied mixture density HMMs for online handwritten digit recognition</atitle><btitle>2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)</btitle><stitle>ICASSP</stitle><date>2003</date><risdate>2003</risdate><volume>2</volume><spage>II</spage><epage>817</epage><pages>II-817</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>9780780376632</isbn><isbn>0780376633</isbn><abstract>This paper describes and evaluates the maximum mutual information criterion (MMI) for online unconstrained-style handwritten digit recognition based on hidden Markov models (HMMs). The study focuses on determining the best MMI optimization scheme and the HMM parameters that exhibit the most discriminative capabilities in the context of tied mixture density hidden Markov models (TDHMMs), where all HMM states share a pool of Gaussians. The experimental results show that the second-order optimization scheme is the most efficient and that although means and covariance matrix are shared by all models, they contribute the most to discrimination.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2003.1202492</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-6149 |
| ispartof | 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03), 2003, Vol.2, p.II-817 |
| issn | 1520-6149 2379-190X |
| language | eng |
| recordid | cdi_ieee_primary_1202492 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Covariance matrix Handheld computers Handwriting recognition Hardware Hidden Markov models Laboratories Maximum likelihood estimation Mutual information Personal digital assistants Power system modeling |
| title | Discriminative training of tied mixture density HMMs for online handwritten digit recognition |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T17%3A20%3A25IST&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=Discriminative%20training%20of%20tied%20mixture%20density%20HMMs%20for%20online%20handwritten%20digit%20recognition&rft.btitle=2003%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech,%20and%20Signal%20Processing,%202003.%20Proceedings.%20(ICASSP%20'03)&rft.au=Nopsuwanchai,%20R.&rft.date=2003&rft.volume=2&rft.spage=II&rft.epage=817&rft.pages=II-817&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=9780780376632&rft.isbn_list=0780376633&rft_id=info:doi/10.1109/ICASSP.2003.1202492&rft_dat=%3Cieee_6IE%3E1202492%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=1202492&rfr_iscdi=true |