Compact Representation of Speech Using 2-D Cepstrum – An Application to Slovak Digits Recognition
HMM speech recogniser with a small number of acoustic observations based on 2-D cepstrum (TDC) is proposed. TDC represents both static and dynamic features of speech implicitly in matrix form. It is shown that TDC analysis enables a compact representation of speech signals. Thus a great advantage of...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 347 |
|---|---|
| container_issue | |
| container_start_page | 342 |
| container_title | |
| container_volume | |
| creator | Jarina, Roman Kuba, Michal Paralic, Martin |
| description | HMM speech recogniser with a small number of acoustic observations based on 2-D cepstrum (TDC) is proposed. TDC represents both static and dynamic features of speech implicitly in matrix form. It is shown that TDC analysis enables a compact representation of speech signals. Thus a great advantage of the proposed model is a massive reduction of speech features used for recognition what lessens computational and memory requirements, so it may be favourable for limited-power ASR applications. Experiments on isolated Slovak digits recognition task show that the method gives comparable results as the conventional MFCC approach. For speech degraded by additive white noise, it reaches better performance than the MFCC method. |
| doi_str_mv | 10.1007/11551874_44 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>pascalfrancis_sprin</sourceid><recordid>TN_cdi_pascalfrancis_primary_17115565</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>17115565</sourcerecordid><originalsourceid>FETCH-LOGICAL-c261t-9be108de584763ea9d2ec0065db31866e78c84787834faa3215018cf1f8ca6b13</originalsourceid><addsrcrecordid>eNpNkLtOwzAYhc1NopROvIAXBoaAf9uxnbFKuUmVkCidI8d1gmkaW3GoxMY78IY8CamKENMZvqMjnQ-hCyDXQIi8AUhTUJIXnB-gSSYVSzlhoECSQzQCAZAwxrOjP0aVVJk4RiPCCE0yydkpOovxjRBCZUZHyOR-E7Tp8bMNnY227XXvfIt9hRfBWvOKl9G1NabJDOc2xL573-Dvzy88bfE0hMaZfb_3eNH4rV7jmatdH4c94-vW7eA5Oql0E-3kN8doeXf7kj8k86f7x3w6TwwV0CdZaYGolU0Vl4JZna2oNYSIdFUOF4WwUpkBDY8Yr7RmFFICylRQKaNFCWyMLve7QUejm6rTrXGxCJ3b6O6jALnTJ9Khd7XvxQG1te2K0vt1LIAUO8vFP8vsBzkoabM</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Compact Representation of Speech Using 2-D Cepstrum – An Application to Slovak Digits Recognition</title><source>Springer Books</source><creator>Jarina, Roman ; Kuba, Michal ; Paralic, Martin</creator><contributor>Pavelka, Tomáš ; Matoušek, Václav ; Mautner, Pavel</contributor><creatorcontrib>Jarina, Roman ; Kuba, Michal ; Paralic, Martin ; Pavelka, Tomáš ; Matoušek, Václav ; Mautner, Pavel</creatorcontrib><description>HMM speech recogniser with a small number of acoustic observations based on 2-D cepstrum (TDC) is proposed. TDC represents both static and dynamic features of speech implicitly in matrix form. It is shown that TDC analysis enables a compact representation of speech signals. Thus a great advantage of the proposed model is a massive reduction of speech features used for recognition what lessens computational and memory requirements, so it may be favourable for limited-power ASR applications. Experiments on isolated Slovak digits recognition task show that the method gives comparable results as the conventional MFCC approach. For speech degraded by additive white noise, it reaches better performance than the MFCC method.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 9783540287896</identifier><identifier>ISBN: 3540287892</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 9783540318170</identifier><identifier>EISBN: 3540318178</identifier><identifier>DOI: 10.1007/11551874_44</identifier><language>eng</language><publisher>Berlin, Heidelberg: Springer Berlin Heidelberg</publisher><subject>Acoustic signal processing ; Acoustics ; Applied sciences ; Artificial intelligence ; Automatic Speech Recognition ; Compact Representation ; Computer science; control theory; systems ; Discrete Cosine Transform ; Exact sciences and technology ; Fundamental areas of phenomenology (including applications) ; Physics ; Speech and sound recognition and synthesis. Linguistics ; Speech Recognition ; Speech Signal</subject><ispartof>Lecture notes in computer science, 2005, p.342-347</ispartof><rights>Springer-Verlag Berlin Heidelberg 2005</rights><rights>2005 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c261t-9be108de584763ea9d2ec0065db31866e78c84787834faa3215018cf1f8ca6b13</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/11551874_44$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/11551874_44$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>309,310,775,776,780,785,786,789,4036,4037,27902,38232,41418,42487</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=17115565$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><contributor>Pavelka, Tomáš</contributor><contributor>Matoušek, Václav</contributor><contributor>Mautner, Pavel</contributor><creatorcontrib>Jarina, Roman</creatorcontrib><creatorcontrib>Kuba, Michal</creatorcontrib><creatorcontrib>Paralic, Martin</creatorcontrib><title>Compact Representation of Speech Using 2-D Cepstrum – An Application to Slovak Digits Recognition</title><title>Lecture notes in computer science</title><description>HMM speech recogniser with a small number of acoustic observations based on 2-D cepstrum (TDC) is proposed. TDC represents both static and dynamic features of speech implicitly in matrix form. It is shown that TDC analysis enables a compact representation of speech signals. Thus a great advantage of the proposed model is a massive reduction of speech features used for recognition what lessens computational and memory requirements, so it may be favourable for limited-power ASR applications. Experiments on isolated Slovak digits recognition task show that the method gives comparable results as the conventional MFCC approach. For speech degraded by additive white noise, it reaches better performance than the MFCC method.</description><subject>Acoustic signal processing</subject><subject>Acoustics</subject><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Automatic Speech Recognition</subject><subject>Compact Representation</subject><subject>Computer science; control theory; systems</subject><subject>Discrete Cosine Transform</subject><subject>Exact sciences and technology</subject><subject>Fundamental areas of phenomenology (including applications)</subject><subject>Physics</subject><subject>Speech and sound recognition and synthesis. Linguistics</subject><subject>Speech Recognition</subject><subject>Speech Signal</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>9783540287896</isbn><isbn>3540287892</isbn><isbn>9783540318170</isbn><isbn>3540318178</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2005</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNpNkLtOwzAYhc1NopROvIAXBoaAf9uxnbFKuUmVkCidI8d1gmkaW3GoxMY78IY8CamKENMZvqMjnQ-hCyDXQIi8AUhTUJIXnB-gSSYVSzlhoECSQzQCAZAwxrOjP0aVVJk4RiPCCE0yydkpOovxjRBCZUZHyOR-E7Tp8bMNnY227XXvfIt9hRfBWvOKl9G1NabJDOc2xL573-Dvzy88bfE0hMaZfb_3eNH4rV7jmatdH4c94-vW7eA5Oql0E-3kN8doeXf7kj8k86f7x3w6TwwV0CdZaYGolU0Vl4JZna2oNYSIdFUOF4WwUpkBDY8Yr7RmFFICylRQKaNFCWyMLve7QUejm6rTrXGxCJ3b6O6jALnTJ9Khd7XvxQG1te2K0vt1LIAUO8vFP8vsBzkoabM</recordid><startdate>2005</startdate><enddate>2005</enddate><creator>Jarina, Roman</creator><creator>Kuba, Michal</creator><creator>Paralic, Martin</creator><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>IQODW</scope></search><sort><creationdate>2005</creationdate><title>Compact Representation of Speech Using 2-D Cepstrum – An Application to Slovak Digits Recognition</title><author>Jarina, Roman ; Kuba, Michal ; Paralic, Martin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c261t-9be108de584763ea9d2ec0065db31866e78c84787834faa3215018cf1f8ca6b13</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2005</creationdate><topic>Acoustic signal processing</topic><topic>Acoustics</topic><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Automatic Speech Recognition</topic><topic>Compact Representation</topic><topic>Computer science; control theory; systems</topic><topic>Discrete Cosine Transform</topic><topic>Exact sciences and technology</topic><topic>Fundamental areas of phenomenology (including applications)</topic><topic>Physics</topic><topic>Speech and sound recognition and synthesis. Linguistics</topic><topic>Speech Recognition</topic><topic>Speech Signal</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jarina, Roman</creatorcontrib><creatorcontrib>Kuba, Michal</creatorcontrib><creatorcontrib>Paralic, Martin</creatorcontrib><collection>Pascal-Francis</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jarina, Roman</au><au>Kuba, Michal</au><au>Paralic, Martin</au><au>Pavelka, Tomáš</au><au>Matoušek, Václav</au><au>Mautner, Pavel</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Compact Representation of Speech Using 2-D Cepstrum – An Application to Slovak Digits Recognition</atitle><btitle>Lecture notes in computer science</btitle><date>2005</date><risdate>2005</risdate><spage>342</spage><epage>347</epage><pages>342-347</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>9783540287896</isbn><isbn>3540287892</isbn><eisbn>9783540318170</eisbn><eisbn>3540318178</eisbn><abstract>HMM speech recogniser with a small number of acoustic observations based on 2-D cepstrum (TDC) is proposed. TDC represents both static and dynamic features of speech implicitly in matrix form. It is shown that TDC analysis enables a compact representation of speech signals. Thus a great advantage of the proposed model is a massive reduction of speech features used for recognition what lessens computational and memory requirements, so it may be favourable for limited-power ASR applications. Experiments on isolated Slovak digits recognition task show that the method gives comparable results as the conventional MFCC approach. For speech degraded by additive white noise, it reaches better performance than the MFCC method.</abstract><cop>Berlin, Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/11551874_44</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0302-9743 |
| ispartof | Lecture notes in computer science, 2005, p.342-347 |
| issn | 0302-9743 1611-3349 |
| language | eng |
| recordid | cdi_pascalfrancis_primary_17115565 |
| source | Springer Books |
| subjects | Acoustic signal processing Acoustics Applied sciences Artificial intelligence Automatic Speech Recognition Compact Representation Computer science control theory systems Discrete Cosine Transform Exact sciences and technology Fundamental areas of phenomenology (including applications) Physics Speech and sound recognition and synthesis. Linguistics Speech Recognition Speech Signal |
| title | Compact Representation of Speech Using 2-D Cepstrum – An Application to Slovak Digits Recognition |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T20%3A08%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pascalfrancis_sprin&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Compact%20Representation%20of%20Speech%20Using%202-D%20Cepstrum%20%E2%80%93%20An%20Application%20to%20Slovak%20Digits%20Recognition&rft.btitle=Lecture%20notes%20in%20computer%20science&rft.au=Jarina,%20Roman&rft.date=2005&rft.spage=342&rft.epage=347&rft.pages=342-347&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=9783540287896&rft.isbn_list=3540287892&rft_id=info:doi/10.1007/11551874_44&rft_dat=%3Cpascalfrancis_sprin%3E17115565%3C/pascalfrancis_sprin%3E%3Curl%3E%3C/url%3E&rft.eisbn=9783540318170&rft.eisbn_list=3540318178&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |