{"id":"https://openalex.org/W1593598571","doi":"https://doi.org/10.21437/interspeech.2008-186","title":"Unsupervised adaptation for HMM-based speech synthesis","display_name":"Unsupervised adaptation for HMM-based speech synthesis","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W1593598571","doi":"https://doi.org/10.21437/interspeech.2008-186","mag":"1593598571"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-186","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/15133765/Unsupervised_adaptation_for_HMM_based_speech_synthesis.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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"],"raw_orcid":null,"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/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"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":"Keiichi Tokuda","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"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":"Heiga Zen","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Philosophy, Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy, Psychology and Language Sciences","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1869","last_page":"1872"},"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":0.9954000115394592,"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":0.9855999946594238,"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":0.8061437606811523},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.764458954334259},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7517651319503784},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6859607696533203},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6360548734664917},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5215746760368347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.502631425857544},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4738509953022003},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4228176474571228},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4013257324695587},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.38672569394111633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061437606811523},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.764458954334259},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7517651319503784},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6859607696533203},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6360548734664917},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5215746760368347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.502631425857544},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4738509953022003},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4228176474571228},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4013257324695587},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.38672569394111633},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"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":5,"locations":[{"id":"doi:10.21437/interspeech.2008-186","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/8b5fc4f0-f92d-4002-a2e8-0c8455f0ba73","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/8b5fc4f0-f92d-4002-a2e8-0c8455f0ba73","pdf_url":"https://www.pure.ed.ac.uk/ws/files/15133765/Unsupervised_adaptation_for_HMM_based_speech_synthesis.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.217.4785","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.217.4785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS080299.PDF","raw_type":"text"},{"id":"pmh:oai:era.ed.ac.uk:1842/3841","is_oa":false,"landing_page_url":"http://hdl.handle.net/1842/3841","pdf_url":null,"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":"Conference Paper"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/8b5fc4f0-f92d-4002-a2e8-0c8455f0ba73","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/8b5fc4f0-f92d-4002-a2e8-0c8455f0ba73","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":"King, S, Tokuda, K, Zen, H & Yamagishi, J 2008, Unsupervised adaptation for HMM-based speech synthesis. in Proc. Interspeech. pp. 1869-1872.","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/8b5fc4f0-f92d-4002-a2e8-0c8455f0ba73","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/8b5fc4f0-f92d-4002-a2e8-0c8455f0ba73","pdf_url":"https://www.pure.ed.ac.uk/ws/files/15133765/Unsupervised_adaptation_for_HMM_based_speech_synthesis.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1593598571.pdf","grobid_xml":"https://content.openalex.org/works/W1593598571.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1979449467","https://openalex.org/W1984905644","https://openalex.org/W2042691334","https://openalex.org/W2116046013","https://openalex.org/W2153914468","https://openalex.org/W2599301895","https://openalex.org/W2915628810"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2039489009"],"abstract_inverted_index":{"It":[0,34],"is":[1,31],"now":[2],"possible":[3],"to":[4,13,56,62],"synthesise":[5],"speech":[6,17,92,102,105],"using":[7,90],"HMMs":[8],"with":[9,47],"a":[10,19,58,64,84],"comparable":[11],"quality":[12],"unit-selection":[14,66],"techniques.":[15],"Generating":[16],"from":[18,93],"model":[20,32,60],"has":[21,35],"many":[22],"potential":[23],"advantages":[24],"over":[25],"concatenating":[26],"waveforms.":[27],"The":[28],"most":[29],"exciting":[30],"adaptation.":[33],"been":[36],"shown":[37],"that":[38],"supervised":[39,69],"speaker":[40,96,110],"adaptation":[41,73],"can":[42],"yield":[43],"highquality":[44],"synthetic":[45],"voices":[46],"an":[48],"order":[49],"of":[50,87],"magnitude":[51],"less":[52],"data":[53,74],"than":[54],"required":[55],"train":[57],"speaker-dependent":[59],"or":[61],"build":[63],"basic":[65],"system.":[67],"Such":[68],"methods":[70],"require":[71],"labelled":[72],"for":[75],"the":[76,94],"target":[77,95],"speaker.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82],"introduce":[83],"method":[85],"capable":[86],"unsupervised":[88],"adaptation,":[89,111],"only":[91],"without":[97],"any":[98],"labelling.":[99],"Index":[100],"Terms:":[101],"synthesis,":[103,106],"HMM-based":[104],"HTS,":[107],"trajectory":[108],"HMMs,":[109],"MLLR":[112]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}