Phonemic recognition using a large hidden Markov model
The authors present a novel method for using the state sequence output of a large hidden Markov model as input to a phonemic recognition system. It thereby demonstrates that a significant amount of speech information is preserved in the most likely state sequences produced by such a model. Two diffe...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on signal processing 1992-06, Vol.40 (6), p.1590-1595 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1595 |
|---|---|
| container_issue | 6 |
| container_start_page | 1590 |
| container_title | IEEE transactions on signal processing |
| container_volume | 40 |
| creator | Pepper, D.J. Clements, M.A. |
| description | The authors present a novel method for using the state sequence output of a large hidden Markov model as input to a phonemic recognition system. It thereby demonstrates that a significant amount of speech information is preserved in the most likely state sequences produced by such a model. Two different system formulations are presented, both achieving recognitions results equivalent to those achieved by other researchers when using systems with similar levels of complexity. The best system formulation achieved a 56.1% recognition rate with 10.8% insertions on a closed-set experiment and a 53.3% recognition rate with 11.8% insertions on a speaker-independent experiment using the TIMIT acoustic-phonetic database. this experiment used 80 male speakers for model training and a separate set of 24 male speakers for model testing.< > |
| doi_str_mv | 10.1109/78.139269 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_139269</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>139269</ieee_id><sourcerecordid>28536257</sourcerecordid><originalsourceid>FETCH-LOGICAL-c277t-3f612fb1203f26cc0a0d5faa6fc382bf2cfc345ad0572786699f6c3a812fdb953</originalsourceid><addsrcrecordid>eNpF0E1LAzEQBuAgCtbqwaunnAQPW_Ox-TpKsSpU9KDgLaTZSRvd3dSkFfz3rqzgaV6YZ-bwInROyYxSYq6VnlFumDQHaEJNTStSK3k4ZCJ4JbR6O0YnpbwTQuvayAmSz5vUQxc9zuDTuo-7mHq8L7FfY4dbl9eAN7FpoMePLn-kL9ylBtpTdBRcW-Dsb07R6-L2ZX5fLZ_uHuY3y8ozpXYVD5KysKKM8MCk98SRRgTnZPBcs1Vgfgi1cA0RiiktpTFBeu70cNWsjOBTdDn-3eb0uYeys10sHtrW9ZD2xTItuGRCDfBqhD6nUjIEu82xc_nbUmJ_m7FK27GZwV6MNgLAvxuXP7c2XY4</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>28536257</pqid></control><display><type>article</type><title>Phonemic recognition using a large hidden Markov model</title><source>IEEE Electronic Library (IEL)</source><creator>Pepper, D.J. ; Clements, M.A.</creator><creatorcontrib>Pepper, D.J. ; Clements, M.A.</creatorcontrib><description>The authors present a novel method for using the state sequence output of a large hidden Markov model as input to a phonemic recognition system. It thereby demonstrates that a significant amount of speech information is preserved in the most likely state sequences produced by such a model. Two different system formulations are presented, both achieving recognitions results equivalent to those achieved by other researchers when using systems with similar levels of complexity. The best system formulation achieved a 56.1% recognition rate with 10.8% insertions on a closed-set experiment and a 53.3% recognition rate with 11.8% insertions on a speaker-independent experiment using the TIMIT acoustic-phonetic database. this experiment used 80 male speakers for model training and a separate set of 24 male speakers for model testing.< ></description><identifier>ISSN: 1053-587X</identifier><identifier>EISSN: 1941-0476</identifier><identifier>DOI: 10.1109/78.139269</identifier><identifier>CODEN: ITPRED</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acoustic signal detection ; Acoustic signal processing ; Array signal processing ; Degradation ; Delay effects ; Detectors ; Filters ; Hidden Markov models ; Oceans ; Signal processing</subject><ispartof>IEEE transactions on signal processing, 1992-06, Vol.40 (6), p.1590-1595</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c277t-3f612fb1203f26cc0a0d5faa6fc382bf2cfc345ad0572786699f6c3a812fdb953</citedby><cites>FETCH-LOGICAL-c277t-3f612fb1203f26cc0a0d5faa6fc382bf2cfc345ad0572786699f6c3a812fdb953</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/139269$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/139269$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Pepper, D.J.</creatorcontrib><creatorcontrib>Clements, M.A.</creatorcontrib><title>Phonemic recognition using a large hidden Markov model</title><title>IEEE transactions on signal processing</title><addtitle>TSP</addtitle><description>The authors present a novel method for using the state sequence output of a large hidden Markov model as input to a phonemic recognition system. It thereby demonstrates that a significant amount of speech information is preserved in the most likely state sequences produced by such a model. Two different system formulations are presented, both achieving recognitions results equivalent to those achieved by other researchers when using systems with similar levels of complexity. The best system formulation achieved a 56.1% recognition rate with 10.8% insertions on a closed-set experiment and a 53.3% recognition rate with 11.8% insertions on a speaker-independent experiment using the TIMIT acoustic-phonetic database. this experiment used 80 male speakers for model training and a separate set of 24 male speakers for model testing.< ></description><subject>Acoustic signal detection</subject><subject>Acoustic signal processing</subject><subject>Array signal processing</subject><subject>Degradation</subject><subject>Delay effects</subject><subject>Detectors</subject><subject>Filters</subject><subject>Hidden Markov models</subject><subject>Oceans</subject><subject>Signal processing</subject><issn>1053-587X</issn><issn>1941-0476</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1992</creationdate><recordtype>article</recordtype><recordid>eNpF0E1LAzEQBuAgCtbqwaunnAQPW_Ox-TpKsSpU9KDgLaTZSRvd3dSkFfz3rqzgaV6YZ-bwInROyYxSYq6VnlFumDQHaEJNTStSK3k4ZCJ4JbR6O0YnpbwTQuvayAmSz5vUQxc9zuDTuo-7mHq8L7FfY4dbl9eAN7FpoMePLn-kL9ylBtpTdBRcW-Dsb07R6-L2ZX5fLZ_uHuY3y8ozpXYVD5KysKKM8MCk98SRRgTnZPBcs1Vgfgi1cA0RiiktpTFBeu70cNWsjOBTdDn-3eb0uYeys10sHtrW9ZD2xTItuGRCDfBqhD6nUjIEu82xc_nbUmJ_m7FK27GZwV6MNgLAvxuXP7c2XY4</recordid><startdate>19920601</startdate><enddate>19920601</enddate><creator>Pepper, D.J.</creator><creator>Clements, M.A.</creator><general>IEEE</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>19920601</creationdate><title>Phonemic recognition using a large hidden Markov model</title><author>Pepper, D.J. ; Clements, M.A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c277t-3f612fb1203f26cc0a0d5faa6fc382bf2cfc345ad0572786699f6c3a812fdb953</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1992</creationdate><topic>Acoustic signal detection</topic><topic>Acoustic signal processing</topic><topic>Array signal processing</topic><topic>Degradation</topic><topic>Delay effects</topic><topic>Detectors</topic><topic>Filters</topic><topic>Hidden Markov models</topic><topic>Oceans</topic><topic>Signal processing</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Pepper, D.J.</creatorcontrib><creatorcontrib>Clements, M.A.</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on signal processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Pepper, D.J.</au><au>Clements, M.A.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Phonemic recognition using a large hidden Markov model</atitle><jtitle>IEEE transactions on signal processing</jtitle><stitle>TSP</stitle><date>1992-06-01</date><risdate>1992</risdate><volume>40</volume><issue>6</issue><spage>1590</spage><epage>1595</epage><pages>1590-1595</pages><issn>1053-587X</issn><eissn>1941-0476</eissn><coden>ITPRED</coden><abstract>The authors present a novel method for using the state sequence output of a large hidden Markov model as input to a phonemic recognition system. It thereby demonstrates that a significant amount of speech information is preserved in the most likely state sequences produced by such a model. Two different system formulations are presented, both achieving recognitions results equivalent to those achieved by other researchers when using systems with similar levels of complexity. The best system formulation achieved a 56.1% recognition rate with 10.8% insertions on a closed-set experiment and a 53.3% recognition rate with 11.8% insertions on a speaker-independent experiment using the TIMIT acoustic-phonetic database. this experiment used 80 male speakers for model training and a separate set of 24 male speakers for model testing.< ></abstract><pub>IEEE</pub><doi>10.1109/78.139269</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1053-587X |
| ispartof | IEEE transactions on signal processing, 1992-06, Vol.40 (6), p.1590-1595 |
| issn | 1053-587X 1941-0476 |
| language | eng |
| recordid | cdi_ieee_primary_139269 |
| source | IEEE Electronic Library (IEL) |
| subjects | Acoustic signal detection Acoustic signal processing Array signal processing Degradation Delay effects Detectors Filters Hidden Markov models Oceans Signal processing |
| title | Phonemic recognition using a large hidden Markov model |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T10%3A23%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Phonemic%20recognition%20using%20a%20large%20hidden%20Markov%20model&rft.jtitle=IEEE%20transactions%20on%20signal%20processing&rft.au=Pepper,%20D.J.&rft.date=1992-06-01&rft.volume=40&rft.issue=6&rft.spage=1590&rft.epage=1595&rft.pages=1590-1595&rft.issn=1053-587X&rft.eissn=1941-0476&rft.coden=ITPRED&rft_id=info:doi/10.1109/78.139269&rft_dat=%3Cproquest_RIE%3E28536257%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=28536257&rft_id=info:pmid/&rft_ieee_id=139269&rfr_iscdi=true |