{"id":"https://openalex.org/W2972667718","doi":"https://doi.org/10.21437/interspeech.2019-2236","title":"StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion","display_name":"StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972667718","doi":"https://doi.org/10.21437/interspeech.2019-2236","mag":"2972667718"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2236","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2236","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020693766","display_name":"Takuhiro Kaneko","orcid":"https://orcid.org/0009-0000-8016-5144"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuhiro Kaneko","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106710403","display_name":"Kou Tanaka","orcid":"https://orcid.org/0009-0003-7107-607X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kou Tanaka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079710814","display_name":"Nobukatsu Hojo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobukatsu Hojo","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020693766"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":11.9939,"has_fulltext":false,"cited_by_count":150,"citation_normalized_percentile":{"value":0.98814632,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"679","last_page":"683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9907000064849854,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6337093710899353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4115634858608246},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3565948009490967},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3562721014022827},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.053153157234191895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6337093710899353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4115634858608246},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3565948009490967},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3562721014022827},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.053153157234191895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-2236","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2236","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6466568207","display_name":"Development of fundamental technology for speech and sound event processing based on complementary use of air- and body-conducted sound signals","funder_award_id":"17H01763","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W49412823","https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1528954144","https://openalex.org/W1588266896","https://openalex.org/W1977362459","https://openalex.org/W1987992317","https://openalex.org/W2022125261","https://openalex.org/W2056852181","https://openalex.org/W2057609679","https://openalex.org/W2086796102","https://openalex.org/W2105160541","https://openalex.org/W2120605154","https://openalex.org/W2123771434","https://openalex.org/W2125389028","https://openalex.org/W2127520494","https://openalex.org/W2142300631","https://openalex.org/W2148846882","https://openalex.org/W2153057929","https://openalex.org/W2156142001","https://openalex.org/W2157412983","https://openalex.org/W2194775991","https://openalex.org/W2396025094","https://openalex.org/W2471520273","https://openalex.org/W2474531669","https://openalex.org/W2475998840","https://openalex.org/W2476548250","https://openalex.org/W2502312327","https://openalex.org/W2518312472","https://openalex.org/W2519091744","https://openalex.org/W2545656684","https://openalex.org/W2567070169","https://openalex.org/W2593414223","https://openalex.org/W2666408839","https://openalex.org/W2746654391","https://openalex.org/W2749651610","https://openalex.org/W2774848319","https://openalex.org/W2787579267","https://openalex.org/W2787748320","https://openalex.org/W2804998325","https://openalex.org/W2902070858","https://openalex.org/W2911708970","https://openalex.org/W2937579788","https://openalex.org/W2946555236","https://openalex.org/W2950776302","https://openalex.org/W2951939904","https://openalex.org/W2962793481","https://openalex.org/W2962896155","https://openalex.org/W2963035245","https://openalex.org/W2963444790","https://openalex.org/W2963539064","https://openalex.org/W2963767194","https://openalex.org/W3023448921","https://openalex.org/W3034420534","https://openalex.org/W4293398859","https://openalex.org/W4308909683","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W1551406738","https://openalex.org/W2610387714","https://openalex.org/W2369308426","https://openalex.org/W1569841287","https://openalex.org/W1512718085","https://openalex.org/W2359001871","https://openalex.org/W2167662847","https://openalex.org/W1560657467"],"abstract_inverted_index":{"Non-parallel":[0],"multi-domain":[1,80],"voice":[2],"conversion":[3],"(VC)":[4],"is":[5,19,55],"a":[6,51,57,83,109,132,146,175],"technique":[7],"for":[8,77],"learning":[9,28],"mappings":[10,30],"among":[11],"multiple":[12,29],"domains":[13],"without":[14],"relying":[15],"on":[16,152],"parallel":[17],"data.This":[18],"important":[20],"but":[21],"challenging":[22],"owing":[23,41],"to":[24,42,45,120,123],"the":[25,32,105,124,128,139,142],"requirement":[26],"of":[27,34,71,141,168,185],"and":[31,61,86,102,171,187],"nonavailability":[33],"explicit":[35],"supervision.Recently,":[36],"StarGAN-VC":[37,182],"has":[38],"garnered":[39],"attention":[40],"its":[43],"ability":[44],"solve":[46],"this":[47,65],"problem":[48],"only":[49],"using":[50],"single":[52,84],"generator.However,":[53],"there":[54],"still":[56],"gap":[58],"between":[59],"real":[60],"converted":[62],"speech.To":[63],"bridge":[64],"gap,":[66],"we":[67,93,107,130],"rethink":[68,94],"conditional":[69,95,111,134],"methods":[70,96,151,162],"StarGAN-VC,":[72],"which":[73],"are":[74],"key":[75],"components":[76],"achieving":[78],"non-parallel":[79,153],"VC":[81],"in":[82,97,145,166,183],"model,":[85],"propose":[87,108],"an":[88],"improved":[89],"variant":[90],"called":[91],"StarGAN-VC2.Particularly,":[92],"two":[98],"aspects:":[99],"training":[100],"objectives":[101],"network":[103],"architectures.For":[104],"former,":[106],"source-and-target":[110],"adversarial":[112],"loss":[113],"that":[114,136,159,179],"allows":[115],"all":[116],"source":[117],"domain":[118,126],"data":[119],"be":[121],"convertible":[122],"target":[125],"data.For":[127],"latter,":[129],"introduce":[131],"modulation-based":[133],"method":[135],"can":[137],"transform":[138],"modulation":[140],"acoustic":[143],"feature":[144],"domain-specific":[147],"manner.We":[148],"evaluated":[149],"our":[150,160],"multi-speaker":[154],"VC.An":[155],"objective":[156],"evaluation":[157,177],"demonstrates":[158],"proposed":[161],"improve":[163],"speech":[164],"quality":[165],"terms":[167,184],"both":[169],"global":[170],"local":[172],"structure":[173],"measures.Furthermore,":[174],"subjective":[176],"shows":[178],"StarGAN-VC2":[180],"outperforms":[181],"naturalness":[186],"speaker":[188],"similarity.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":31},{"year":2020,"cited_by_count":28},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}