{"id":"https://openalex.org/W2937579788","doi":"https://doi.org/10.1109/icassp.2019.8682897","title":"Cyclegan-VC2: Improved Cyclegan-based Non-parallel Voice Conversion","display_name":"Cyclegan-VC2: Improved Cyclegan-based Non-parallel Voice Conversion","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2937579788","doi":"https://doi.org/10.1109/icassp.2019.8682897","mag":"2937579788"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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"],"raw_orcid":null,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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":20.315,"has_fulltext":false,"cited_by_count":275,"citation_normalized_percentile":{"value":0.99467204,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6820","last_page":"6824"},"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":0.9990000128746033,"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":0.9959999918937683,"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/naturalness","display_name":"Naturalness","score":0.8211214542388916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7890510559082031},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5981271862983704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5609090328216553},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.42301759123802185},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.41797080636024475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4168775677680969},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32489919662475586},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.09440332651138306}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8211214542388916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890510559082031},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5981271862983704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5609090328216553},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.42301759123802185},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.41797080636024475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4168775677680969},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32489919662475586},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.09440332651138306},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.49000000953674316}],"awards":[],"funders":[{"id":"https://openalex.org/F4320333435","display_name":"Virginia Agricultural Experiment Station, Virginia Polytechnic Institute and State University","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W49412823","https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1588266896","https://openalex.org/W1903029394","https://openalex.org/W1974745215","https://openalex.org/W1977362459","https://openalex.org/W2022125261","https://openalex.org/W2056852181","https://openalex.org/W2057609679","https://openalex.org/W2086796102","https://openalex.org/W2099471712","https://openalex.org/W2105160541","https://openalex.org/W2120605154","https://openalex.org/W2123771434","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/W2339754110","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/W2567070169","https://openalex.org/W2586453598","https://openalex.org/W2593414223","https://openalex.org/W2598581049","https://openalex.org/W2666408839","https://openalex.org/W2746654391","https://openalex.org/W2747744257","https://openalex.org/W2749651610","https://openalex.org/W2774848319","https://openalex.org/W2787748320","https://openalex.org/W2804998325","https://openalex.org/W2887264325","https://openalex.org/W2902070858","https://openalex.org/W2911708970","https://openalex.org/W2949382160","https://openalex.org/W2951939904","https://openalex.org/W2962793481","https://openalex.org/W2962896155","https://openalex.org/W2963035245","https://openalex.org/W2963073614","https://openalex.org/W2963444790","https://openalex.org/W2963539064","https://openalex.org/W2963970792","https://openalex.org/W2964069186","https://openalex.org/W2964121744","https://openalex.org/W2964341837","https://openalex.org/W4293398859","https://openalex.org/W4320013936","https://openalex.org/W6602007935","https://openalex.org/W6631190155","https://openalex.org/W6635216677","https://openalex.org/W6703724764","https://openalex.org/W6711854987","https://openalex.org/W6724804524","https://openalex.org/W6730095352","https://openalex.org/W6731370813","https://openalex.org/W6735204497","https://openalex.org/W6746801104","https://openalex.org/W6754095682"],"related_works":["https://openalex.org/W4293320219","https://openalex.org/W2953246223","https://openalex.org/W4283584549","https://openalex.org/W2554314924","https://openalex.org/W4288256692","https://openalex.org/W2998859928","https://openalex.org/W4381885966","https://openalex.org/W2969399009","https://openalex.org/W4398186750","https://openalex.org/W3151498616"],"abstract_inverted_index":{"Non-parallel":[0],"voice":[1],"conversion":[2],"(VC)":[3],"is":[4,22,66,93],"a":[5,43,49,68,83,122],"technique":[6,132],"for":[7,186],"learning":[8],"the":[9,33,36,72,87,128,144,150],"mapping":[10],"from":[11],"source":[12],"to":[13,32,48,149],"target":[14,74,151],"speech":[15],"without":[16,53],"relying":[17,54],"on":[18,55,121],"parallel":[19,50],"data.":[20],"This":[21],"an":[23,94,103],"important":[24],"task,":[25],"but":[26],"it":[27],"has":[28,41],"been":[29],"challenging":[30],"due":[31],"disadvantages":[34],"of":[35,97,130,154,182],"training":[37],"conditions.":[38],"Recently,":[39],"CycleGAN-VC":[40,98,179],"provided":[42],"breakthrough":[44],"and":[45,75,78,113,126,157,167,184,192],"performed":[46],"comparably":[47],"VC":[51,124],"method":[52,120],"any":[56],"extra":[57],"data,":[58],"modules,":[59],"or":[60],"time":[61],"alignment":[62],"procedures.":[63],"However,":[64],"there":[65],"still":[67],"large":[69],"gap":[70,81],"between":[71],"real":[73],"converted":[76,145],"speech,":[77],"bridging":[79],"this":[80],"remains":[82],"challenge.":[84],"To":[85],"reduce":[86],"gap,":[88],"we":[89,161],"propose":[90],"CycleGAN-VC2,":[91],"which":[92,160],"improved":[95,104,109,114],"version":[96],"incorporating":[99],"three":[100],"new":[101],"techniques:":[102],"objective":[105,136],"(two-step":[106],"adversarial":[107],"losses),":[108],"generator":[110],"(2-1-2D":[111],"CNN),":[112],"discriminator":[115],"(PatchGAN).":[116],"We":[117],"evaluated":[118],"our":[119],"non-parallel":[123],"task":[125],"analyzed":[127],"effect":[129],"each":[131],"in":[133,152,180],"detail.":[134],"An":[135],"evaluation":[137,174],"showed":[138,175],"that":[139,176],"these":[140],"techniques":[141],"help":[142],"bring":[143],"feature":[146],"sequence":[147],"closer":[148],"terms":[153,181],"both":[155],"global":[156],"local":[158],"structures,":[159],"assess":[162],"by":[163],"using":[164],"Mel-cepstral":[165],"distortion":[166],"modulation":[168],"spectra":[169],"distance,":[170],"respectively.":[171],"A":[172],"subjective":[173],"CycleGAN-VC2":[177],"outperforms":[178],"naturalness":[183],"similarity":[185],"every":[187],"speaker":[188],"pair,":[189],"including":[190],"intra-gender":[191],"inter-gender":[193],"pairs.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":36},{"year":2023,"cited_by_count":57},{"year":2022,"cited_by_count":39},{"year":2021,"cited_by_count":46},{"year":2020,"cited_by_count":38},{"year":2019,"cited_by_count":17}],"updated_date":"2026-05-29T09:21:14.243279","created_date":"2025-10-10T00:00:00"}