{"id":"https://openalex.org/W2153914468","doi":"https://doi.org/10.1109/tasl.2008.2006647","title":"Analysis of Speaker Adaptation Algorithms for HMM-Based Speech Synthesis and a Constrained SMAPLR Adaptation Algorithm","display_name":"Analysis of Speaker Adaptation Algorithms for HMM-Based Speech Synthesis and a Constrained SMAPLR Adaptation Algorithm","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2153914468","doi":"https://doi.org/10.1109/tasl.2008.2006647","mag":"2153914468"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2008.2006647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2006647","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://era.ed.ac.uk/bitstream/1842/3902/1/04740153.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":[{"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":"Junichi Yamagishi","raw_affiliation_strings":["Center of Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","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":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024469014","display_name":"Yuji Nakano","orcid":null},"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":"Yuji Nakano","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112500870","display_name":"Katsumi Ogata","orcid":null},"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":"Katsumi Ogata","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033660872","display_name":"Juri Isogai","orcid":null},"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":"Juri Isogai","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":44.8899,"has_fulltext":true,"cited_by_count":330,"citation_normalized_percentile":{"value":0.99844119,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"17","issue":"1","first_page":"66","last_page":"83"},"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/T10860","display_name":"Speech and Audio Processing","score":0.996999979019165,"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":0.9876999855041504,"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/adaptation","display_name":"Adaptation (eye)","score":0.7649860978126526},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6410818696022034},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6250045895576477},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5810894966125488},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5608059167861938},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08096683025360107}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7649860978126526},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6410818696022034},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6250045895576477},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5810894966125488},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5608059167861938},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08096683025360107},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tasl.2008.2006647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2006647","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/3902","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3902","pdf_url":"https://era.ed.ac.uk/bitstream/1842/3902/1/04740153.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.860.3351","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.860.3351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.era.lib.ed.ac.uk/bitstream/handle/1842/3902/04740153.pdf%3Bjsessionid%3D72E3403FFAF53CCF51607E85B84C1007?sequence%3D1","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/3902","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3902","pdf_url":"https://era.ed.ac.uk/bitstream/1842/3902/1/04740153.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[{"id":"https://openalex.org/G665036903","display_name":"Realization of average-voice-based speech synthesis with diverse voices and speaking styles","funder_award_id":"15300055","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320332","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90"},{"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/W2153914468.pdf","grobid_xml":"https://content.openalex.org/works/W2153914468.grobid-xml"},"referenced_works_count":75,"referenced_works":["https://openalex.org/W42451021","https://openalex.org/W129217914","https://openalex.org/W153299664","https://openalex.org/W167766911","https://openalex.org/W187033940","https://openalex.org/W284180566","https://openalex.org/W300119222","https://openalex.org/W428433050","https://openalex.org/W1512429158","https://openalex.org/W1537908555","https://openalex.org/W1559184314","https://openalex.org/W1572730534","https://openalex.org/W1591172823","https://openalex.org/W1599512239","https://openalex.org/W1600722501","https://openalex.org/W1602430027","https://openalex.org/W1605997703","https://openalex.org/W1861150963","https://openalex.org/W1935012542","https://openalex.org/W1963627370","https://openalex.org/W1970501224","https://openalex.org/W1984905644","https://openalex.org/W1995565802","https://openalex.org/W2000513720","https://openalex.org/W2002342963","https://openalex.org/W2009417200","https://openalex.org/W2036039036","https://openalex.org/W2037740282","https://openalex.org/W2039800941","https://openalex.org/W2040025757","https://openalex.org/W2048973497","https://openalex.org/W2049633694","https://openalex.org/W2064218608","https://openalex.org/W2081976287","https://openalex.org/W2085013480","https://openalex.org/W2087110403","https://openalex.org/W2093450784","https://openalex.org/W2096555739","https://openalex.org/W2096980176","https://openalex.org/W2100969003","https://openalex.org/W2104075463","https://openalex.org/W2105080323","https://openalex.org/W2106554350","https://openalex.org/W2106792148","https://openalex.org/W2121981798","https://openalex.org/W2124629003","https://openalex.org/W2132373255","https://openalex.org/W2144139079","https://openalex.org/W2145575463","https://openalex.org/W2146871184","https://openalex.org/W2149175990","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2158942523","https://openalex.org/W2159150199","https://openalex.org/W2167152389","https://openalex.org/W2400063444","https://openalex.org/W2484208911","https://openalex.org/W4300060217","https://openalex.org/W6601724279","https://openalex.org/W6605232188","https://openalex.org/W6606842542","https://openalex.org/W6607663849","https://openalex.org/W6610316872","https://openalex.org/W6610697106","https://openalex.org/W6630838124","https://openalex.org/W6633512198","https://openalex.org/W6635376843","https://openalex.org/W6636404455","https://openalex.org/W6636435764","https://openalex.org/W6639125025","https://openalex.org/W6679758046","https://openalex.org/W6683730234","https://openalex.org/W6712610176","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"In":[0],"this":[1,55],"paper,":[2],"we":[3,20,68,112,140,164],"analyze":[4],"the":[5,51,59,74,79,82,86,89,106,109,119,123,130,134,137,142,158,161,166,179,185,198,221],"effects":[6],"of":[7,61,73,81,96,108,122,129,136,160,181,225],"several":[8,63,97,182,214],"factors":[9],"and":[10,16,25,57,94,102,118,154,190,212,216,223],"configuration":[11],"choices":[12],"encountered":[13],"during":[14],"training":[15,83],"model":[17],"construction":[18],"when":[19],"want":[21],"to":[22,126],"obtain":[23],"better":[24],"more":[26],"stable":[27],"adaptation":[28,38,65,100,196,205,230],"in":[29,54,228],"HMM-based":[30,232],"speech":[31,209,233],"synthesis.":[32,234],"We":[33,177,202],"then":[34],"propose":[35],"a":[36,170],"new":[37],"algorithm":[39],"called":[40,174],"constrained":[41],"structural":[42,175],"maximumaposteriorilinear":[43],"regression":[44,99,188,200],"(CSMAPLR)":[45],"whose":[46],"derivation":[47],"is":[48],"based":[49],"on":[50,58],"knowledge":[52],"obtained":[53],"analysis":[56],"results":[60,219],"comparing":[62],"conventional":[64],"algorithms.":[66,104,201],"Here,":[67],"investigate":[69],"six":[70],"major":[71],"aspects":[72],"speaker":[75,229],"adaptation:":[76],"initial":[77,87,110],"models;":[78,88],"amount":[80],"data":[84],"for":[85,145,151,184,231],"transform":[90,138,143],"functions,":[91,139],"estimation":[92,162,172],"criteria,":[93,163],"sensitivity":[95,180],"linear":[98,187,199],"algorithms;":[101],"combination":[103],"Analyzing":[105,133,157],"effect":[107,135,159],"model,":[111],"compare":[113,141,165],"speaker-dependent":[114],"models,":[115,117],"gender-independent":[116],"simultaneous":[120],"use":[121,128],"gender-dependent":[124,131],"models":[125],"single":[127],"models.":[132],"function":[144],"only":[146],"mean":[147,152],"vectors":[148,153],"with":[149,169,197],"that":[150],"covariance":[155],"matrices.":[156],"ML":[167],"criterion":[168,173],"robust":[171],"MAP.":[176],"evaluate":[178],"thresholds":[183],"piecewise":[186],"algorithms":[189,206,227],"take":[191],"up":[192],"methods":[193],"combining":[194],"MAP":[195],"incorporate":[203],"these":[204,226],"into":[207],"our":[208],"synthesis":[210],"system":[211],"present":[213],"subjective":[215],"objective":[217],"evaluation":[218],"showing":[220],"utility":[222],"effectiveness":[224]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":34},{"year":2015,"cited_by_count":42},{"year":2014,"cited_by_count":37},{"year":2013,"cited_by_count":35},{"year":2012,"cited_by_count":37}],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2025-10-10T00:00:00"}