Loading…
Syllabic Markov models of Arabic HMMs of spoken Arabic using CV units
We survey evidence - orthographic distributional phonological and psycholinguistic - in favor of a model of Arabic speech sounds based on the CV unit and extensive use of the silent sukuun vowel. We then construct a small-vocabulary multi-speaker CV HMM similar to the phonemic HMMs based on tied tri...
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 | 259 |
| container_issue | |
| container_start_page | 254 |
| container_title | |
| container_volume | |
| creator | Ingleby, Michael Baothman, Fatmah |
| description | We survey evidence - orthographic distributional phonological and psycholinguistic - in favor of a model of Arabic speech sounds based on the CV unit and extensive use of the silent sukuun vowel. We then construct a small-vocabulary multi-speaker CV HMM similar to the phonemic HMMs based on tied triphones that are widely used in speech recognizers for English and other European languages. Using experimental measures of recognition accuracy and trainability, we demonstrate that the CV type of model outperforms a standard tied triphone recognizer for Arabic speech, using Cohen's kappa ration for statistical comparison. Finally we argue that models based on CV units may also lead to better stemmers, spell-checkers and other natural language processing tools for Arabic. |
| doi_str_mv | 10.1109/CIST.2014.7016628 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_7016628</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7016628</ieee_id><sourcerecordid>7016628</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-3fc3d5825358e5dfce005e800f0b385ac6f2c486cd544cf60eaf1a7a8172f7b73</originalsourceid><addsrcrecordid>eNo1j81Kw0AURkdQsNQ8gLiZF0i885e5syyh2kKDi1ZxVyaTGRmbJiXTCn17odbV4TuLDw4hjwwKxsA8V8v1puDAZKGBlSXHG5IZjUxqY5TRht-SCRdc5wzV5z3JUvoGAMEQjRQTMl-fu8420dHajrvhh-6H1neJDoHOxotf1PVlpsOw8_2_PaXYf9Hqg576eEwP5C7YLvnsyil5f5lvqkW-entdVrNVHplWx1wEJ1qFXAmFXrXBeQDlESBAI1BZVwbuJJauVVK6UIK3gVltkWkedKPFlDz9_Ubv_fYwxr0dz9truPgFvDZLSw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Syllabic Markov models of Arabic HMMs of spoken Arabic using CV units</title><source>IEEE Xplore All Conference Series</source><creator>Ingleby, Michael ; Baothman, Fatmah</creator><creatorcontrib>Ingleby, Michael ; Baothman, Fatmah</creatorcontrib><description>We survey evidence - orthographic distributional phonological and psycholinguistic - in favor of a model of Arabic speech sounds based on the CV unit and extensive use of the silent sukuun vowel. We then construct a small-vocabulary multi-speaker CV HMM similar to the phonemic HMMs based on tied triphones that are widely used in speech recognizers for English and other European languages. Using experimental measures of recognition accuracy and trainability, we demonstrate that the CV type of model outperforms a standard tied triphone recognizer for Arabic speech, using Cohen's kappa ration for statistical comparison. Finally we argue that models based on CV units may also lead to better stemmers, spell-checkers and other natural language processing tools for Arabic.</description><identifier>ISSN: 2327-185X</identifier><identifier>EISBN: 9781479959792</identifier><identifier>EISBN: 1479959782</identifier><identifier>EISBN: 1479959790</identifier><identifier>EISBN: 9781479959785</identifier><identifier>DOI: 10.1109/CIST.2014.7016628</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accuracy ; Hidden Markov models ; kappa ratio ; Natural language processing ; Speech ; Speech recognition ; speech recognizers ; syllabic components ; testing speaker independence ; tied triphone models ; Training ; Vocabulary</subject><ispartof>2014 Third IEEE International Colloquium in Information Science and Technology (CIST), 2014, p.254-259</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/7016628$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,27902,54530,54907</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7016628$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ingleby, Michael</creatorcontrib><creatorcontrib>Baothman, Fatmah</creatorcontrib><title>Syllabic Markov models of Arabic HMMs of spoken Arabic using CV units</title><title>2014 Third IEEE International Colloquium in Information Science and Technology (CIST)</title><addtitle>CIST</addtitle><description>We survey evidence - orthographic distributional phonological and psycholinguistic - in favor of a model of Arabic speech sounds based on the CV unit and extensive use of the silent sukuun vowel. We then construct a small-vocabulary multi-speaker CV HMM similar to the phonemic HMMs based on tied triphones that are widely used in speech recognizers for English and other European languages. Using experimental measures of recognition accuracy and trainability, we demonstrate that the CV type of model outperforms a standard tied triphone recognizer for Arabic speech, using Cohen's kappa ration for statistical comparison. Finally we argue that models based on CV units may also lead to better stemmers, spell-checkers and other natural language processing tools for Arabic.</description><subject>Accuracy</subject><subject>Hidden Markov models</subject><subject>kappa ratio</subject><subject>Natural language processing</subject><subject>Speech</subject><subject>Speech recognition</subject><subject>speech recognizers</subject><subject>syllabic components</subject><subject>testing speaker independence</subject><subject>tied triphone models</subject><subject>Training</subject><subject>Vocabulary</subject><issn>2327-185X</issn><isbn>9781479959792</isbn><isbn>1479959782</isbn><isbn>1479959790</isbn><isbn>9781479959785</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2014</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1j81Kw0AURkdQsNQ8gLiZF0i885e5syyh2kKDi1ZxVyaTGRmbJiXTCn17odbV4TuLDw4hjwwKxsA8V8v1puDAZKGBlSXHG5IZjUxqY5TRht-SCRdc5wzV5z3JUvoGAMEQjRQTMl-fu8420dHajrvhh-6H1neJDoHOxotf1PVlpsOw8_2_PaXYf9Hqg576eEwP5C7YLvnsyil5f5lvqkW-entdVrNVHplWx1wEJ1qFXAmFXrXBeQDlESBAI1BZVwbuJJauVVK6UIK3gVltkWkedKPFlDz9_Ubv_fYwxr0dz9truPgFvDZLSw</recordid><startdate>201410</startdate><enddate>201410</enddate><creator>Ingleby, Michael</creator><creator>Baothman, Fatmah</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201410</creationdate><title>Syllabic Markov models of Arabic HMMs of spoken Arabic using CV units</title><author>Ingleby, Michael ; Baothman, Fatmah</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-3fc3d5825358e5dfce005e800f0b385ac6f2c486cd544cf60eaf1a7a8172f7b73</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Accuracy</topic><topic>Hidden Markov models</topic><topic>kappa ratio</topic><topic>Natural language processing</topic><topic>Speech</topic><topic>Speech recognition</topic><topic>speech recognizers</topic><topic>syllabic components</topic><topic>testing speaker independence</topic><topic>tied triphone models</topic><topic>Training</topic><topic>Vocabulary</topic><toplevel>online_resources</toplevel><creatorcontrib>Ingleby, Michael</creatorcontrib><creatorcontrib>Baothman, Fatmah</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>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>Ingleby, Michael</au><au>Baothman, Fatmah</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Syllabic Markov models of Arabic HMMs of spoken Arabic using CV units</atitle><btitle>2014 Third IEEE International Colloquium in Information Science and Technology (CIST)</btitle><stitle>CIST</stitle><date>2014-10</date><risdate>2014</risdate><spage>254</spage><epage>259</epage><pages>254-259</pages><issn>2327-185X</issn><eisbn>9781479959792</eisbn><eisbn>1479959782</eisbn><eisbn>1479959790</eisbn><eisbn>9781479959785</eisbn><abstract>We survey evidence - orthographic distributional phonological and psycholinguistic - in favor of a model of Arabic speech sounds based on the CV unit and extensive use of the silent sukuun vowel. We then construct a small-vocabulary multi-speaker CV HMM similar to the phonemic HMMs based on tied triphones that are widely used in speech recognizers for English and other European languages. Using experimental measures of recognition accuracy and trainability, we demonstrate that the CV type of model outperforms a standard tied triphone recognizer for Arabic speech, using Cohen's kappa ration for statistical comparison. Finally we argue that models based on CV units may also lead to better stemmers, spell-checkers and other natural language processing tools for Arabic.</abstract><pub>IEEE</pub><doi>10.1109/CIST.2014.7016628</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2327-185X |
| ispartof | 2014 Third IEEE International Colloquium in Information Science and Technology (CIST), 2014, p.254-259 |
| issn | 2327-185X |
| language | eng |
| recordid | cdi_ieee_primary_7016628 |
| source | IEEE Xplore All Conference Series |
| subjects | Accuracy Hidden Markov models kappa ratio Natural language processing Speech Speech recognition speech recognizers syllabic components testing speaker independence tied triphone models Training Vocabulary |
| title | Syllabic Markov models of Arabic HMMs of spoken Arabic using CV units |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-24T03%3A36%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Syllabic%20Markov%20models%20of%20Arabic%20HMMs%20of%20spoken%20Arabic%20using%20CV%20units&rft.btitle=2014%20Third%20IEEE%20International%20Colloquium%20in%20Information%20Science%20and%20Technology%20(CIST)&rft.au=Ingleby,%20Michael&rft.date=2014-10&rft.spage=254&rft.epage=259&rft.pages=254-259&rft.issn=2327-185X&rft_id=info:doi/10.1109/CIST.2014.7016628&rft.eisbn=9781479959792&rft.eisbn_list=1479959782&rft.eisbn_list=1479959790&rft.eisbn_list=9781479959785&rft_dat=%3Cieee_CHZPO%3E7016628%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-3fc3d5825358e5dfce005e800f0b385ac6f2c486cd544cf60eaf1a7a8172f7b73%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=7016628&rfr_iscdi=true |