{"id":"https://openalex.org/W2921290812","doi":"https://doi.org/10.23919/apsipa.2018.8659621","title":"Unsupervised Speaker Adaptation for DNN-based Speech Synthesis using Input Codes","display_name":"Unsupervised Speaker Adaptation for DNN-based Speech Synthesis using Input Codes","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921290812","doi":"https://doi.org/10.23919/apsipa.2018.8659621","mag":"2921290812"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659621","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/c71369dc-1494-4183-9511-cff80c520079","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063931518","display_name":"Yoshikazu Nishimura","orcid":"https://orcid.org/0000-0003-3153-3339"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshikazu Nishimura","raw_affiliation_strings":["Alt Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Alt Inc., Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062895056"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":0.4887,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74572916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"133","issue":null,"first_page":"649","last_page":"658"},"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":0.9991999864578247,"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":0.9929999709129333,"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":0.7809641361236572},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7525783777236938},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6231309771537781},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4611080288887024},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.453967422246933},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41243401169776917},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06941086053848267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809641361236572},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7525783777236938},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6231309771537781},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4611080288887024},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.453967422246933},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41243401169776917},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06941086053848267},{"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:10.23919/apsipa.2018.8659621","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/c71369dc-1494-4183-9511-cff80c520079","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c71369dc-1494-4183-9511-cff80c520079","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":"Takaki, S, Nishimura, Y & Yamagishi, J 2019, Unsupervised Speaker Adaptation for DNN-based Speech Synthesis using Input Codes. in Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2018. Institute of Electrical and Electronics Engineers, Honolulu, Hawaii, USA, pp. 649-658, Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2018, Honolulu, Hawaii, United States, 12/11/18. https://doi.org/10.23919/APSIPA.2018.8659621","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/c71369dc-1494-4183-9511-cff80c520079","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/8659621","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/c71369dc-1494-4183-9511-cff80c520079","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c71369dc-1494-4183-9511-cff80c520079","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":"Takaki, S, Nishimura, Y & Yamagishi, J 2019, Unsupervised Speaker Adaptation for DNN-based Speech Synthesis using Input Codes. in Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2018. Institute of Electrical and Electronics Engineers, Honolulu, Hawaii, USA, pp. 649-658, Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2018, Honolulu, Hawaii, United States, 12/11/18. https://doi.org/10.23919/APSIPA.2018.8659621","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1492383498","https://openalex.org/W1593598571","https://openalex.org/W1983108229","https://openalex.org/W1996304098","https://openalex.org/W2006129368","https://openalex.org/W2012086895","https://openalex.org/W2041823554","https://openalex.org/W2094147890","https://openalex.org/W2156692643","https://openalex.org/W2401698713","https://openalex.org/W2406312423","https://openalex.org/W2407024733","https://openalex.org/W2507389969","https://openalex.org/W2516321201","https://openalex.org/W2516559027","https://openalex.org/W2605320104","https://openalex.org/W2619368999","https://openalex.org/W2736900972","https://openalex.org/W2746498480","https://openalex.org/W2759925408","https://openalex.org/W2963712897","https://openalex.org/W4232282348","https://openalex.org/W6683161958","https://openalex.org/W6713727690","https://openalex.org/W6736204136"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"A":[0,157],"new":[1,66,83,158],"speaker-adaptation":[2],"technique":[3,24,221,247],"for":[4,256],"deep":[5],"neural":[6],"network":[7],"(DNN)-based":[8],"speech":[9,15,170,204,262],"synthesis":[10],"-":[11,20],"which":[12,106,149],"requires":[13],"only":[14,226],"data":[16,171,229],"without":[17,126],"orthographic":[18],"transcriptions":[19],"is":[21,25,89,161,188],"proposed.":[22],"This":[23],"based":[26],"on":[27,178],"a":[28,56,65,80,145,166,254],"DNN-based":[29,261],"speech-synthesis":[30,147,199],"model":[31,58,98,200],"that":[32,69,190,205,244],"takes":[33],"speaker,":[34],"gender,":[35],"and":[36,43,59,130,213,235],"age":[37],"into":[38,196],"consideration":[39],"as":[40,140],"additional":[41],"inputs":[42],"outputs":[44,150],"acoustic":[45,71,151],"parameters":[46,152],"of":[47,75,99,134,153,169,181,218,240],"corresponding":[48],"voices":[49],"from":[50,96],"text":[51,127],"in":[52,79,110,260],"order":[53],"to":[54,73,116,142,251],"construct":[55,253],"multi-speaker":[57,146,198],"perform":[60],"speaker":[61,112,119,177,185,259],"adaptation.":[62],"It":[63,187],"uses":[64],"input":[67,84,141],"code":[68],"represents":[70],"similarity":[72],"each":[74,97],"the":[76,100,118,131,135,154,179,182,192,197,207,219,241,245,257],"training":[77,101,136,155],"speakers":[78,137],"probability.":[81],"The":[82,238],"code,":[85],"called":[86],"\u201cspeaker-similarity":[87],"vector,\u201d":[88],"obtained":[90],"by":[91,164,173],"concatenating":[92],"posterior":[93],"probabilities":[94],"calculated":[95],"speakers.":[102,156],"GMM-UBM":[103],"or":[104],"i-vector/PLDA,":[105],"are":[107,114,138],"widely":[108],"used":[109,115,125,139],"text-independent":[111],"verification,":[113],"represent":[117],"models,":[120],"since":[121],"they":[122],"can":[123,201],"be":[124],"information.":[128],"Text":[129],"speaker-similarity":[132,159,194],"vectors":[133],"first":[143],"train":[144],"model,":[148],"vector":[160,195],"then":[162],"estimated":[163,193],"using":[165,224],"small":[167],"amount":[168],"uttered":[172],"an":[174],"unknown":[175],"target":[176,208,258],"basis":[180],"separately":[183],"trained":[184],"models.":[186],"expected":[189],"inputting":[191],"generate":[202],"synthetic":[203],"resembles":[206],"speaker's":[209],"voice.":[210],"In":[211],"objective":[212],"subjective":[214],"experiments,":[215],"adaptation":[216,228],"performance":[217],"proposed":[220,246],"was":[222],"evaluated":[223],"not":[225],"studio-quality":[227],"but":[230],"also":[231],"low-quality":[232],"(i.e.,":[233],"noisy":[234],"reverberant)":[236],"data.":[237],"results":[239],"experiments":[242],"indicate":[243],"makes":[248],"it":[249],"possible":[250],"rapidly":[252],"voice":[255],"synthesis.":[263]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}