Optimal Phonemic Environmental Range to Select VCV Instances for VCV Speech Synthesis by Rule
We proposed two selection methods, 1) selection method by using phonemic environmental resemblance score (PER method), and 2) selection method by searching minimal connective distortion path (MLD method), for small scale speech synthesis system. PER method requires phonemic environmental information...
Gespeichert in:
| Veröffentlicht in: | Denki Gakkai ronbunshi. C, Erekutoronikusu, joho kogaku, shisutemu Information and Systems, 2003, Vol.123(3), pp.467-474 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 474 |
|---|---|
| container_issue | 3 |
| container_start_page | 467 |
| container_title | Denki Gakkai ronbunshi. C, Erekutoronikusu, joho kogaku, shisutemu |
| container_volume | 123 |
| creator | Shimizu, Tadaaki Kimoto, Masaya Yoshimura, Hiroki Namiki, Toshie Isu, Naoki Sugata, Kazuhiro |
| description | We proposed two selection methods, 1) selection method by using phonemic environmental resemblance score (PER method), and 2) selection method by searching minimal connective distortion path (MLD method), for small scale speech synthesis system. PER method requires phonemic environmental information for each VCV instance in a VCV unit dictionary. This paper investigated experimentally to what extent we can reduce the phonemic environmental information with keeping high quality of synthesized speech. We verified that two phonemes frontward and one phoneme rearward range to a current VCV instance is enough to synthesize similar quality of speech as five phonemes frontward and five phonemes rearward. This result gives an experimental basis on minimizing a size of VCV unit dictionary. |
| doi_str_mv | 10.1541/ieejeiss.123.467 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_1433876233</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3076300641</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2447-70c799f7d727135d0c77a2578ca471821ce2ee1c2cba6d7818defaf0520af3213</originalsourceid><addsrcrecordid>eNpVkEFrAjEQhUNpoWK99xjoeW0myZp4LKKtIFi09VZCjLO6smZtshb8902rFXqZYR7vm2EeIffAupBLeCwRt1jG2AUuurKnrkgLhNSZhjy_Ji0mdJ5JzuGWdGIsl4xxqYUCaJGP6b4pd7air5va4650dOi_ylD7HfomyTPr10ibms6xQtfQxWBBxz421juMtKjDrzLfI7oNnR99s8FYRro80tmhwjtyU9gqYufc2-R9NHwbvGST6fN48DTJHJdSZYo51e8XaqW4ApGv0qgsz5V2VirQHBxyRHDcLW1vpTToFRa2YDlnthAcRJs8nPbuQ_15wNiYbX0IPp00IIXQqseFSC52crlQxxiwMPuQfg9HA8z85Gj-cjQpR5NyTMjohGzTy2u8ADY0pavwPyDONYEXg9vYYNCLb112gK8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1433876233</pqid></control><display><type>article</type><title>Optimal Phonemic Environmental Range to Select VCV Instances for VCV Speech Synthesis by Rule</title><source>EZB-FREE-00999 freely available EZB journals</source><creator>Shimizu, Tadaaki ; Kimoto, Masaya ; Yoshimura, Hiroki ; Namiki, Toshie ; Isu, Naoki ; Sugata, Kazuhiro</creator><creatorcontrib>Shimizu, Tadaaki ; Kimoto, Masaya ; Yoshimura, Hiroki ; Namiki, Toshie ; Isu, Naoki ; Sugata, Kazuhiro</creatorcontrib><description>We proposed two selection methods, 1) selection method by using phonemic environmental resemblance score (PER method), and 2) selection method by searching minimal connective distortion path (MLD method), for small scale speech synthesis system. PER method requires phonemic environmental information for each VCV instance in a VCV unit dictionary. This paper investigated experimentally to what extent we can reduce the phonemic environmental information with keeping high quality of synthesized speech. We verified that two phonemes frontward and one phoneme rearward range to a current VCV instance is enough to synthesize similar quality of speech as five phonemes frontward and five phonemes rearward. This result gives an experimental basis on minimizing a size of VCV unit dictionary.</description><identifier>ISSN: 0385-4221</identifier><identifier>EISSN: 1348-8155</identifier><identifier>DOI: 10.1541/ieejeiss.123.467</identifier><language>eng</language><publisher>Tokyo: The Institute of Electrical Engineers of Japan</publisher><subject>connective distortion ; LSP analysis ; phonemic environment ; synthesis unit selection ; VCV Speech synthesis</subject><ispartof>IEEJ Transactions on Electronics, Information and Systems, 2003, Vol.123(3), pp.467-474</ispartof><rights>2003 by the Institute of Electrical Engineers of Japan</rights><rights>Copyright Japan Science and Technology Agency 2003</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c2447-70c799f7d727135d0c77a2578ca471821ce2ee1c2cba6d7818defaf0520af3213</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,4021,27921,27922,27923</link.rule.ids></links><search><creatorcontrib>Shimizu, Tadaaki</creatorcontrib><creatorcontrib>Kimoto, Masaya</creatorcontrib><creatorcontrib>Yoshimura, Hiroki</creatorcontrib><creatorcontrib>Namiki, Toshie</creatorcontrib><creatorcontrib>Isu, Naoki</creatorcontrib><creatorcontrib>Sugata, Kazuhiro</creatorcontrib><title>Optimal Phonemic Environmental Range to Select VCV Instances for VCV Speech Synthesis by Rule</title><title>Denki Gakkai ronbunshi. C, Erekutoronikusu, joho kogaku, shisutemu</title><addtitle>IEEJ Trans. EIS</addtitle><description>We proposed two selection methods, 1) selection method by using phonemic environmental resemblance score (PER method), and 2) selection method by searching minimal connective distortion path (MLD method), for small scale speech synthesis system. PER method requires phonemic environmental information for each VCV instance in a VCV unit dictionary. This paper investigated experimentally to what extent we can reduce the phonemic environmental information with keeping high quality of synthesized speech. We verified that two phonemes frontward and one phoneme rearward range to a current VCV instance is enough to synthesize similar quality of speech as five phonemes frontward and five phonemes rearward. This result gives an experimental basis on minimizing a size of VCV unit dictionary.</description><subject>connective distortion</subject><subject>LSP analysis</subject><subject>phonemic environment</subject><subject>synthesis unit selection</subject><subject>VCV Speech synthesis</subject><issn>0385-4221</issn><issn>1348-8155</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2003</creationdate><recordtype>article</recordtype><recordid>eNpVkEFrAjEQhUNpoWK99xjoeW0myZp4LKKtIFi09VZCjLO6smZtshb8902rFXqZYR7vm2EeIffAupBLeCwRt1jG2AUuurKnrkgLhNSZhjy_Ji0mdJ5JzuGWdGIsl4xxqYUCaJGP6b4pd7air5va4650dOi_ylD7HfomyTPr10ibms6xQtfQxWBBxz421juMtKjDrzLfI7oNnR99s8FYRro80tmhwjtyU9gqYufc2-R9NHwbvGST6fN48DTJHJdSZYo51e8XaqW4ApGv0qgsz5V2VirQHBxyRHDcLW1vpTToFRa2YDlnthAcRJs8nPbuQ_15wNiYbX0IPp00IIXQqseFSC52crlQxxiwMPuQfg9HA8z85Gj-cjQpR5NyTMjohGzTy2u8ADY0pavwPyDONYEXg9vYYNCLb112gK8</recordid><startdate>2003</startdate><enddate>2003</enddate><creator>Shimizu, Tadaaki</creator><creator>Kimoto, Masaya</creator><creator>Yoshimura, Hiroki</creator><creator>Namiki, Toshie</creator><creator>Isu, Naoki</creator><creator>Sugata, Kazuhiro</creator><general>The Institute of Electrical Engineers of Japan</general><general>Japan Science and Technology Agency</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>2003</creationdate><title>Optimal Phonemic Environmental Range to Select VCV Instances for VCV Speech Synthesis by Rule</title><author>Shimizu, Tadaaki ; Kimoto, Masaya ; Yoshimura, Hiroki ; Namiki, Toshie ; Isu, Naoki ; Sugata, Kazuhiro</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2447-70c799f7d727135d0c77a2578ca471821ce2ee1c2cba6d7818defaf0520af3213</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2003</creationdate><topic>connective distortion</topic><topic>LSP analysis</topic><topic>phonemic environment</topic><topic>synthesis unit selection</topic><topic>VCV Speech synthesis</topic><toplevel>online_resources</toplevel><creatorcontrib>Shimizu, Tadaaki</creatorcontrib><creatorcontrib>Kimoto, Masaya</creatorcontrib><creatorcontrib>Yoshimura, Hiroki</creatorcontrib><creatorcontrib>Namiki, Toshie</creatorcontrib><creatorcontrib>Isu, Naoki</creatorcontrib><creatorcontrib>Sugata, Kazuhiro</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications 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>Denki Gakkai ronbunshi. C, Erekutoronikusu, joho kogaku, shisutemu</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shimizu, Tadaaki</au><au>Kimoto, Masaya</au><au>Yoshimura, Hiroki</au><au>Namiki, Toshie</au><au>Isu, Naoki</au><au>Sugata, Kazuhiro</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Optimal Phonemic Environmental Range to Select VCV Instances for VCV Speech Synthesis by Rule</atitle><jtitle>Denki Gakkai ronbunshi. C, Erekutoronikusu, joho kogaku, shisutemu</jtitle><addtitle>IEEJ Trans. EIS</addtitle><date>2003</date><risdate>2003</risdate><volume>123</volume><issue>3</issue><spage>467</spage><epage>474</epage><pages>467-474</pages><issn>0385-4221</issn><eissn>1348-8155</eissn><abstract>We proposed two selection methods, 1) selection method by using phonemic environmental resemblance score (PER method), and 2) selection method by searching minimal connective distortion path (MLD method), for small scale speech synthesis system. PER method requires phonemic environmental information for each VCV instance in a VCV unit dictionary. This paper investigated experimentally to what extent we can reduce the phonemic environmental information with keeping high quality of synthesized speech. We verified that two phonemes frontward and one phoneme rearward range to a current VCV instance is enough to synthesize similar quality of speech as five phonemes frontward and five phonemes rearward. This result gives an experimental basis on minimizing a size of VCV unit dictionary.</abstract><cop>Tokyo</cop><pub>The Institute of Electrical Engineers of Japan</pub><doi>10.1541/ieejeiss.123.467</doi><tpages>8</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0385-4221 |
| ispartof | IEEJ Transactions on Electronics, Information and Systems, 2003, Vol.123(3), pp.467-474 |
| issn | 0385-4221 1348-8155 |
| language | eng |
| recordid | cdi_proquest_journals_1433876233 |
| source | EZB-FREE-00999 freely available EZB journals |
| subjects | connective distortion LSP analysis phonemic environment synthesis unit selection VCV Speech synthesis |
| title | Optimal Phonemic Environmental Range to Select VCV Instances for VCV Speech Synthesis by Rule |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T12%3A18%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Optimal%20Phonemic%20Environmental%20Range%20to%20Select%20VCV%20Instances%20for%20VCV%20Speech%20Synthesis%20by%20Rule&rft.jtitle=Denki%20Gakkai%20ronbunshi.%20C,%20Erekutoronikusu,%20joho%20kogaku,%20shisutemu&rft.au=Shimizu,%20Tadaaki&rft.date=2003&rft.volume=123&rft.issue=3&rft.spage=467&rft.epage=474&rft.pages=467-474&rft.issn=0385-4221&rft.eissn=1348-8155&rft_id=info:doi/10.1541/ieejeiss.123.467&rft_dat=%3Cproquest_cross%3E3076300641%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1433876233&rft_id=info:pmid/&rfr_iscdi=true |