{"id":"https://openalex.org/W1580849279","doi":"https://doi.org/10.21437/interspeech.2009-140","title":"Thousands of voices for HMM-based speech synthesis","display_name":"Thousands of voices for HMM-based speech synthesis","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W1580849279","doi":"https://doi.org/10.21437/interspeech.2009-140","mag":"1580849279"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-140","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/15115004/Thousands_of_Voices_for_HMM_based_Speech_Synthesis.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Philosophy, Psychology and Language Sciences"],"affiliations":[{"raw_affiliation_string":"School of Philosophy, Psychology and Language Sciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058936597","display_name":"Bela Usabaev","orcid":null},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bela Usabaev","raw_affiliation_strings":["Universit\u00e4t T\u00fcbingen"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t T\u00fcbingen","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["School of Philosophy Psychology and Language Sciences"],"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105301736","display_name":"John Dines","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"John Dines","raw_affiliation_strings":["Idiap Research Institute, Martigny-Combe, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103093321","display_name":"Jilei Tian","orcid":"https://orcid.org/0000-0002-4588-9398"},"institutions":[{"id":"https://openalex.org/I4210106018","display_name":"Nokia (Netherlands)","ror":"https://ror.org/01resg468","country_code":"NL","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210106018"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jilei Tian","raw_affiliation_strings":["Nokia"],"affiliations":[{"raw_affiliation_string":"Nokia","institution_ids":["https://openalex.org/I4210106018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109250475","display_name":"Rile Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210106018","display_name":"Nokia (Netherlands)","ror":"https://ror.org/01resg468","country_code":"NL","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210106018"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Rile Hu","raw_affiliation_strings":["Nokia"],"affiliations":[{"raw_affiliation_string":"Nokia","institution_ids":["https://openalex.org/I4210106018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719922","display_name":"Yong Guan","orcid":"https://orcid.org/0000-0002-9044-2595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Guan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049909008","display_name":"Keiichiro Oura","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichiro Oura","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["National Institute of Information and Communications Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023689975","display_name":"Reima Karhila","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reima Karhila","raw_affiliation_strings":["Helsinki University of Technology"],"affiliations":[{"raw_affiliation_string":"Helsinki University of Technology","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":["Helsinki University of Technology"],"affiliations":[{"raw_affiliation_string":"Helsinki University of Technology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5007639385"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.6586,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97138651,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"420","last_page":"423"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9961000084877014,"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/T10860","display_name":"Speech and Audio Processing","score":0.9944999814033508,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8450962901115417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.819355845451355},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7447255849838257},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6676569581031799},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5010042190551758},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41929054260253906},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4177798926830292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39134302735328674}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8450962901115417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819355845451355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7447255849838257},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6676569581031799},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5010042190551758},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41929054260253906},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4177798926830292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39134302735328674},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2009-140","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/72134a56-c936-4f78-b37c-6d0398a7a8c5","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=70450161300&partnerID=8YFLogxK","pdf_url":"https://www.pure.ed.ac.uk/ws/files/15115004/Thousands_of_Voices_for_HMM_based_Speech_Synthesis.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.644.3964","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.644.3964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2009/index.php","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/72134a56-c936-4f78-b37c-6d0398a7a8c5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/72134a56-c936-4f78-b37c-6d0398a7a8c5","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yamagishi, J, Usabaev, B, King, S, Watts, O, Dines, J, Tian, J, Hu, R, Guan, Y, Oura, K, Tokuda, K, Karhila, R & Kurimo, M 2009, Thousands of voices for HMM-based speech synthesis. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 : 10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009; Brighton, United Kingdom. pp. 420-423.","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/72134a56-c936-4f78-b37c-6d0398a7a8c5","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=70450161300&partnerID=8YFLogxK","pdf_url":"https://www.pure.ed.ac.uk/ws/files/15115004/Thousands_of_Voices_for_HMM_based_Speech_Synthesis.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1361938442","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1580849279.pdf"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1529897604","https://openalex.org/W1600722501","https://openalex.org/W2117418893","https://openalex.org/W2119929864","https://openalex.org/W2400063444","https://openalex.org/W4252316495"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2904846757"],"abstract_inverted_index":{"Our":[0],"recent":[1],"experiments":[2],"with":[3,38],"HMM-based":[4,12,99],"speech":[5,13,29,100,137],"synthesis":[6,14,101],"systems":[7],"have":[8,104],"demonstrated":[9],"that":[10,31,41,47,102],"speaker-adaptive":[11],"(which":[15],"uses":[16],"an":[17,84],"\u2018average":[18],"voice":[19],"model":[20,23],"\u2019":[21,61],"plus":[22],"adaptation)":[24],"is":[25],"robust":[26],"to":[27,79],"non-ideal":[28],"data":[30],"are":[32,42],"recorded":[33],"under":[34],"various":[35],"conditions":[36],"and":[37,122,130],"varying":[39],"micro-phones,":[40],"not":[43],"perfectly":[44],"clean,":[45],"and/or":[46],"lack":[48],"of":[49,75,82,87,96],"pho-netic":[50],"balance.":[51],"This":[52],"enables":[53],"us":[54],"consider":[55],"building":[56],"high-quality":[57],"voices":[58,88,97],"on":[59],"\u2019non-TTS":[60],"corpora":[62,69,110],"such":[63,111],"as":[64,112],"ASR":[65,68,109],"corpora.":[66],"Since":[67],"generally":[70],"include":[71],"a":[72],"large":[73],"number":[74,86],"speakers,":[76],"this":[77,91],"leads":[78],"the":[80,113,132],"possibility":[81],"producing":[83],"enormous":[85],"automatically.":[89],"In":[90],"paper":[92],"we":[93,103],"show":[94],"thousands":[95],"for":[98],"made":[105],"from":[106],"several":[107],"popular":[108],"Wall":[114],"Street":[115],"Journal":[116],"databases":[117],"(WSJ0/WSJ1/WSJCAM0),":[118],"Resource":[119],"Management,":[120],"Globalphone":[121],"Speecon.":[123],"We":[124],"report":[125],"some":[126],"perceptual":[127],"evalu-ation":[128],"results":[129],"outline":[131],"outstanding":[133],"issues.":[134],"Index":[135],"Terms:":[136],"synthesis,":[138],"HMMs,":[139],"speaker":[140],"adaptation":[141],"1.":[142]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
