{"id":"https://openalex.org/W3006777338","doi":"https://doi.org/10.1109/asru46091.2019.9004008","title":"Bootstrapping Non-Parallel Voice Conversion from Speaker-Adaptive Text-to-Speech","display_name":"Bootstrapping Non-Parallel Voice Conversion from Speaker-Adaptive Text-to-Speech","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3006777338","doi":"https://doi.org/10.1109/asru46091.2019.9004008","mag":"3006777338"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9004008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004008","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/a7a8c46d-0a82-40c9-8178-228ddc6e333b","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/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"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"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/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":["The University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002145453"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":2.2402,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91111431,"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":"200","last_page":"207"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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/T10028","display_name":"Topic Modeling","score":0.9959999918937683,"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":0.855976402759552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7316606044769287},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.6705667972564697},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5988795757293701},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45504772663116455},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.43790683150291443},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42541033029556274},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.424567848443985},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38739925622940063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37556958198547363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.855976402759552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7316606044769287},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6705667972564697},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5988795757293701},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45504772663116455},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.43790683150291443},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42541033029556274},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.424567848443985},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38739925622940063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37556958198547363},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru46091.2019.9004008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004008","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/a7a8c46d-0a82-40c9-8178-228ddc6e333b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/a7a8c46d-0a82-40c9-8178-228ddc6e333b","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":"Luong, H-T & Yamagishi, J 2020, Bootstrapping Non-Parallel Voice Conversion From Speaker-Adaptive Text-to-Speech. in 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Institute of Electrical and Electronics Engineers, pp. 200-207, IEEE Automatic Speech Recognition and Understanding Workshop 2019, Sentosa, Singapore, 14/12/19. https://doi.org/10.1109/ASRU46091.2019.9004008","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/a7a8c46d-0a82-40c9-8178-228ddc6e333b","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/document/9004008","pdf_url":null,"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 & Yamagishi, J 2020, Bootstrapping Non-Parallel Voice Conversion From Speaker-Adaptive Text-to-Speech. in 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Institute of Electrical and Electronics Engineers, pp. 200-207, IEEE Automatic Speech Recognition and Understanding Workshop 2019, Sentosa, Singapore, 14/12/19. https://doi.org/10.1109/ASRU46091.2019.9004008","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/a7a8c46d-0a82-40c9-8178-228ddc6e333b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/a7a8c46d-0a82-40c9-8178-228ddc6e333b","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":"Luong, H-T & Yamagishi, J 2020, Bootstrapping Non-Parallel Voice Conversion From Speaker-Adaptive Text-to-Speech. in 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Institute of Electrical and Electronics Engineers, pp. 200-207, IEEE Automatic Speech Recognition and Understanding Workshop 2019, Sentosa, Singapore, 14/12/19. https://doi.org/10.1109/ASRU46091.2019.9004008","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W33533989","https://openalex.org/W49412823","https://openalex.org/W113498433","https://openalex.org/W1538607601","https://openalex.org/W1570629387","https://openalex.org/W1588266896","https://openalex.org/W1974745215","https://openalex.org/W1981457580","https://openalex.org/W2013996527","https://openalex.org/W2035962301","https://openalex.org/W2086796102","https://openalex.org/W2120605154","https://openalex.org/W2134202996","https://openalex.org/W2156142001","https://openalex.org/W2161476805","https://openalex.org/W2507912506","https://openalex.org/W2518172956","https://openalex.org/W2527729766","https://openalex.org/W2532494225","https://openalex.org/W2774848319","https://openalex.org/W2800289214","https://openalex.org/W2808706139","https://openalex.org/W2885820941","https://openalex.org/W2887264325","https://openalex.org/W2889329491","https://openalex.org/W2899877258","https://openalex.org/W2938583109","https://openalex.org/W2940544976","https://openalex.org/W2947445680","https://openalex.org/W2950224550","https://openalex.org/W2950414763","https://openalex.org/W2962739369","https://openalex.org/W2963035245","https://openalex.org/W2963432880","https://openalex.org/W2963808252","https://openalex.org/W2964069186","https://openalex.org/W2972374322","https://openalex.org/W2972867623","https://openalex.org/W2972999331","https://openalex.org/W2973034126","https://openalex.org/W2977798327","https://openalex.org/W3101689408","https://openalex.org/W4298174729","https://openalex.org/W6602007935","https://openalex.org/W6632366324","https://openalex.org/W6635216677","https://openalex.org/W6679569544","https://openalex.org/W6726528559"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2184127972","https://openalex.org/W2012356448","https://openalex.org/W1573084162","https://openalex.org/W2389353568","https://openalex.org/W2571917423","https://openalex.org/W2404901909","https://openalex.org/W2105439218","https://openalex.org/W2765293924","https://openalex.org/W3006777338"],"abstract_inverted_index":{"Voice":[0],"conversion":[1],"(VC)":[2],"and":[3,48,133],"text-to-speech":[4],"(TTS)":[5],"are":[6,22],"two":[7,59],"tasks":[8],"that":[9,113],"share":[10],"a":[11,17,35,39,43,83,101],"similar":[12],"objective,":[13],"generating":[14],"speech":[15,89,99,136],"with":[16],"target":[18,87],"voice.":[19],"However,":[20],"they":[21],"usually":[23],"developed":[24],"independently":[25],"under":[26],"vastly":[27],"different":[28],"frameworks.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"propose":[34],"methodology":[36],"to":[37,68,105,119],"bootstrap":[38],"VC":[40,77],"system":[41,78],"from":[42],"pretrained":[44],"speaker-adaptive":[45],"TTS":[46,74],"model":[47],"unify":[49],"the":[50,55,64,69,73,95,107,114,126],"techniques":[51],"as":[52,54],"well":[53],"interpretations":[56],"of":[57,72,86,97],"these":[58],"tasks.":[60],"Moreover":[61],"by":[62],"offloading":[63],"heavy":[65],"data":[66],"demand":[67],"training":[70],"stage":[71],"model,":[75],"our":[76],"can":[79],"be":[80],"built":[81],"using":[82,98,135],"small":[84],"amount":[85],"speaker":[88],"data.":[90],"It":[91],"also":[92,131],"opens":[93],"up":[94],"possibility":[96],"in":[100,125,138],"foreign":[102],"unseen":[103,140],"language":[104],"build":[106],"system.":[108],"Our":[109],"subjective":[110],"evaluations":[111],"show":[112],"proposed":[115],"framework":[116],"is":[117],"able":[118],"not":[120],"only":[121],"achieve":[122],"competitive":[123],"performance":[124],"standard":[127],"intra-language":[128],"scenario":[129],"but":[130],"adapt":[132],"convert":[134],"utterances":[137],"an":[139],"language.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}