{"id":"https://openalex.org/W2972595148","doi":"https://doi.org/10.21437/interspeech.2019-1311","title":"Training Multi-Speaker Neural Text-to-Speech Systems Using Speaker-Imbalanced Speech Corpora","display_name":"Training Multi-Speaker Neural Text-to-Speech Systems Using Speaker-Imbalanced Speech Corpora","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972595148","doi":"https://doi.org/10.21437/interspeech.2019-1311","mag":"2972595148"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1311","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/99989927/Training_Multi_Speaker_Neural_LUONG_DoA170619_AFV.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002145453","display_name":"Hieu-Thi Luong","orcid":"https://orcid.org/0000-0002-4772-5995"},"institutions":[{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"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":"Hieu-Thi Luong","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","SOKENDAI (The Graduate University for Advanced Studies), Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"SOKENDAI (The Graduate University for Advanced Studies), Kanagawa, Japan","institution_ids":["https://openalex.org/I200475212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"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":"Xin Wang","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/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"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"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":["GB","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["SOKENDAI (The Graduate University for Advanced Studies), Kanagawa, Japan","National Institute of Informatics, Tokyo, Japan","University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"SOKENDAI (The Graduate University for Advanced Studies), Kanagawa, Japan","institution_ids":["https://openalex.org/I200475212"]},{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035313377","display_name":"Nobuyuki Nishizawa","orcid":"https://orcid.org/0009-0007-6242-5695"},"institutions":[{"id":"https://openalex.org/I4210164495","display_name":"KDDI Research (Japan)","ror":"https://ror.org/05qsqt662","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210164495"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuyuki Nishizawa","raw_affiliation_strings":["KDDI Research Inc., Saitama, Japan"],"affiliations":[{"raw_affiliation_string":"KDDI Research Inc., Saitama, Japan","institution_ids":["https://openalex.org/I4210164495"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002145453"],"corresponding_institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"],"apc_list":null,"apc_paid":null,"fwci":2.7435,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.92629974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1303","last_page":"1307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.972000002861023,"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/T10028","display_name":"Topic Modeling","score":0.9485999941825867,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8115059733390808},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7551096677780151},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5730485320091248},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5001058578491211},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.49834108352661133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46128031611442566},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41687339544296265},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4160847067832947},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41055572032928467},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3702547550201416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115059733390808},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7551096677780151},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5730485320091248},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5001058578491211},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.49834108352661133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46128031611442566},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41687339544296265},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4160847067832947},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41055572032928467},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3702547550201416}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-1311","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f5b78a11-f604-4bd3-b45d-bb9841c8236d","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f5b78a11-f604-4bd3-b45d-bb9841c8236d","pdf_url":"https://www.pure.ed.ac.uk/ws/files/99989927/Training_Multi_Speaker_Neural_LUONG_DoA170619_AFV.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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Luong, H-T, Wang, X, Yamagishi, J & Nishizawa, N 2019, Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora. in Proceedings Interspeech 2019. International Speech Communication Association, pp. 1303-1307, Interspeech 2019, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-1311","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/f5b78a11-f604-4bd3-b45d-bb9841c8236d","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f5b78a11-f604-4bd3-b45d-bb9841c8236d","pdf_url":"https://www.pure.ed.ac.uk/ws/files/99989927/Training_Multi_Speaker_Neural_LUONG_DoA170619_AFV.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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Luong, H-T, Wang, X, Yamagishi, J & Nishizawa, N 2019, Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora. in Proceedings Interspeech 2019. International Speech Communication Association, pp. 1303-1307, Interspeech 2019, Graz, Austria, 15/09/19. https://doi.org/10.21437/Interspeech.2019-1311","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2972595148.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W85350352","https://openalex.org/W1492383498","https://openalex.org/W2148143831","https://openalex.org/W2162248535","https://openalex.org/W2165143604","https://openalex.org/W2395106899","https://openalex.org/W2508418541","https://openalex.org/W2516559027","https://openalex.org/W2519091744","https://openalex.org/W2543721542","https://openalex.org/W2595110011","https://openalex.org/W2749074593","https://openalex.org/W2786868129","https://openalex.org/W2787685498","https://openalex.org/W2801493797","https://openalex.org/W2808706139","https://openalex.org/W2886022419","https://openalex.org/W2889129899","https://openalex.org/W2892620417","https://openalex.org/W2913512413","https://openalex.org/W2963542120","https://openalex.org/W2964243274"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":{"When":[0],"the":[1,68,78,85,142,145],"available":[2,97,136],"data":[3,23,48,71,87,98,154],"of":[4,70,84,135,144],"a":[5,12,29,45,63,104,133],"target":[6],"speaker":[7,74,101],"is":[8,75,130,155],"insufficient":[9],"to":[10,81,102,115],"train":[11,28,103],"high":[13],"quality":[14,59,143],"speaker-dependent":[15,64,117],"neural":[16,39],"text-to-speech":[17],"(TTS)":[18],"system,":[19],"we":[20,138],"can":[21,53,139],"combine":[22],"from":[24,49,72,99],"multiple":[25,50],"speakers":[26,51,151],"and":[27,60],"multi-speaker":[30,40,105,124],"TTS":[31,41],"model":[32,42,106],"instead.":[33],"Many":[34],"studies":[35],"have":[36],"shown":[37],"that":[38,93],"trained":[43,131],"with":[44,57],"small":[46],"amount":[47,69],"combined":[52],"generate":[54],"synthetic":[55,146],"speech":[56,147],"better":[58,108],"stability":[61],"than":[62,109],"one.":[65],"However":[66],"when":[67],"each":[73,128],"highly":[76],"unbalanced,":[77],"best":[79],"approach":[80],"make":[82],"use":[83],"excessive":[86],"remains":[88],"unknown.":[89],"Our":[90],"experiments":[91],"showed":[92],"simply":[94],"combining":[95],"all":[96],"every":[100],"produces":[107],"or":[110],"at":[111],"least":[112],"similar":[113],"performance":[114],"its":[116],"counterpart.":[118],"Moreover":[119],"by":[120],"using":[121],"an":[122],"ensemble":[123],"model,":[125],"in":[126],"which":[127],"subsystem":[129],"on":[132],"subset":[134],"data,":[137],"further":[140],"improve":[141],"especially":[148],"for":[149],"underrepresented":[150],"whose":[152],"training":[153],"limited.<br/><br/>":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}