{"id":"https://openalex.org/W2100140000","doi":"https://doi.org/10.1109/jstsp.2013.2283461","title":"Statistical Parametric Speech Synthesis Based on Gaussian Process Regression","display_name":"Statistical Parametric Speech Synthesis Based on Gaussian Process Regression","publication_year":2013,"publication_date":"2013-09-25","ids":{"openalex":"https://openalex.org/W2100140000","doi":"https://doi.org/10.1109/jstsp.2013.2283461","mag":"2100140000"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2013.2283461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2013.2283461","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100668101/ATD100000413/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024181978","display_name":"Tomoki Koriyama","orcid":"https://orcid.org/0000-0002-8347-5604"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Koriyama","raw_affiliation_strings":["Department of Information Processing, Tokyo Institute of Technology, Yokohama, Japan","Dept. of Inf. Process., Tokyo Inst. of Technol., Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Processing, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Dept. of Inf. Process., Tokyo Inst. of Technol., Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Department of Information Processing, Tokyo Institute of Technology, Yokohama, Japan","Dept. of Inf. Process., Tokyo Inst. of Technol., Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Processing, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Dept. of Inf. Process., Tokyo Inst. of Technol., Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022405100","display_name":"Takao Kobayashi","orcid":"https://orcid.org/0000-0003-0387-8030"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takao Kobayashi","raw_affiliation_strings":["Department of Information Processing, Tokyo Institute of Technology, Yokohama, Japan","Dept. of Inf. Process., Tokyo Inst. of Technol., Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Processing, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Dept. of Inf. Process., Tokyo Inst. of Technol., Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":10.7089,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.98151223,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"8","issue":"2","first_page":"173","last_page":"183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7522139549255371},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7104121446609497},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5733415484428406},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.566627025604248},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5658233761787415},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5486897826194763},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5032183527946472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4231330156326294},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3392166495323181},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3040943741798401},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17136415839195251},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12429383397102356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522139549255371},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7104121446609497},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5733415484428406},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.566627025604248},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5658233761787415},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5486897826194763},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5032183527946472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4231330156326294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3392166495323181},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3040943741798401},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17136415839195251},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12429383397102356},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2013.2283461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2013.2283461","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50233275","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100668101","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100668101/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:t2r2.star.titech.ac.jp:50233275","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100668101","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100668101/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1573140883","display_name":"Research on advanced robust speech synthesis and its applications to multi-lingual speech communication","funder_award_id":"24300071","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1897481696","display_name":"Research on speech synthesis using non-parametric modeling based on Gaussian process regression","funder_award_id":"25540065","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5973663496","display_name":"A study of speech synthesis for achieving synthetic speech with high quality and variability based on hybrid approach","funder_award_id":"25730106","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7425592821","display_name":"\u81ea\u7136\u306a\u30d2\u30e5\u30fc\u30de\u30f3\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30a4\u30f3\u30bf\u30e9\u30af\u30b7\u30e7\u30f3\u306e\u305f\u3081\u306e\u8a71\u3057\u8a00\u8449\u4f1a\u8a71\u97f3\u58f0\u5408\u6210","funder_award_id":"13J08776","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2100140000.pdf","grobid_xml":"https://content.openalex.org/works/W2100140000.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W200094172","https://openalex.org/W1510073064","https://openalex.org/W1531312258","https://openalex.org/W1568585903","https://openalex.org/W1571870753","https://openalex.org/W1576213419","https://openalex.org/W1580216809","https://openalex.org/W1600722501","https://openalex.org/W1935012542","https://openalex.org/W1963627370","https://openalex.org/W1965255698","https://openalex.org/W1979449467","https://openalex.org/W2000513720","https://openalex.org/W2010602269","https://openalex.org/W2049686551","https://openalex.org/W2090761477","https://openalex.org/W2099768828","https://openalex.org/W2102003408","https://openalex.org/W2106792148","https://openalex.org/W2107860279","https://openalex.org/W2108674328","https://openalex.org/W2109915598","https://openalex.org/W2111194146","https://openalex.org/W2129142580","https://openalex.org/W2134477639","https://openalex.org/W2143029619","https://openalex.org/W2154644810","https://openalex.org/W2154649109","https://openalex.org/W2162351465","https://openalex.org/W2165255420","https://openalex.org/W2179117922","https://openalex.org/W2432517183","https://openalex.org/W4211049957","https://openalex.org/W4229875153","https://openalex.org/W6631924718","https://openalex.org/W6634689341","https://openalex.org/W6674989108","https://openalex.org/W6675380101","https://openalex.org/W6676044216","https://openalex.org/W6676358011","https://openalex.org/W6680220816","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W2995886640","https://openalex.org/W1591475660","https://openalex.org/W2001275470","https://openalex.org/W2169866437","https://openalex.org/W1964286703"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"statistical":[4],"parametric":[5],"speech":[6,97,116],"synthesis":[7,93,98,117],"technique":[8,104],"based":[9],"on":[10,29],"Gaussian":[11,69],"process":[12],"regression":[13],"(GPR).":[14],"The":[15,38,86],"GPR":[16],"model":[17,114],"is":[18,33,56],"designed":[19],"for":[20,89],"directly":[21],"predicting":[22],"frame-level":[23],"acoustic":[24],"features":[25,107],"from":[26,35],"corresponding":[27],"information":[28,54],"frame":[30,39,48],"context":[31,40],"that":[32,100],"obtained":[34],"linguistic":[36],"information.":[37],"includes":[41],"the":[42,46,50,59,83,101,110],"relative":[43],"position":[44],"of":[45],"current":[47],"within":[49],"phone":[51,92],"and":[52,55,75,94],"articulatory":[53],"used":[57],"as":[58],"explanatory":[60],"variable":[61],"in":[62],"GPR.":[63],"Here,":[64],"we":[65],"introduce":[66],"cluster-based":[67],"sparse":[68],"processes":[70],"(GPs),":[71],"i.e.,":[72],"local":[73],"GPs":[74],"partially":[76],"independent":[77],"conditional":[78],"(PIC)":[79],"approximation,":[80],"to":[81],"reduce":[82],"computational":[84],"cost.":[85],"experimental":[87],"results":[88],"both":[90],"isolated":[91],"full-sentence":[95],"continuous":[96],"revealed":[99],"proposed":[102],"GPR-based":[103],"without":[105],"dynamic":[106,124],"slightly":[108],"outperformed":[109],"conventional":[111],"hidden":[112],"Markov":[113],"(HMM)-based":[115],"using":[118],"minimum":[119],"generation":[120],"error":[121],"training":[122],"with":[123],"features.":[125]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}