{"id":"https://openalex.org/W3095936335","doi":"https://doi.org/10.21437/interspeech.2020-2280","title":"CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-Spectrogram Conversion","display_name":"CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-Spectrogram Conversion","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095936335","doi":"https://doi.org/10.21437/interspeech.2020-2280","mag":"3095936335"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2280","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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":9.5769,"has_fulltext":false,"cited_by_count":97,"citation_normalized_percentile":{"value":0.988511,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2017","last_page":"2021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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/T11309","display_name":"Music and Audio Processing","score":0.9868999719619751,"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/spectrogram","display_name":"Spectrogram","score":0.9338456392288208},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7237735986709595},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7233715057373047},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5722337961196899},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44241440296173096},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.43397772312164307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4305417537689209},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.365171879529953}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9338456392288208},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7237735986709595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233715057373047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5722337961196899},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44241440296173096},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.43397772312164307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4305417537689209},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.365171879529953},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2280","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W2022125261","https://openalex.org/W2056852181","https://openalex.org/W2120605154","https://openalex.org/W2142300631","https://openalex.org/W2148846882","https://openalex.org/W2156142001","https://openalex.org/W2157412983","https://openalex.org/W2194775991","https://openalex.org/W2339754110","https://openalex.org/W2471520273","https://openalex.org/W2474531669","https://openalex.org/W2502312327","https://openalex.org/W2518172956","https://openalex.org/W2518312472","https://openalex.org/W2532494225","https://openalex.org/W2567070169","https://openalex.org/W2593414223","https://openalex.org/W2666408839","https://openalex.org/W2747744257","https://openalex.org/W2774848319","https://openalex.org/W2804998325","https://openalex.org/W2902070858","https://openalex.org/W2937579788","https://openalex.org/W2945478979","https://openalex.org/W2946555236","https://openalex.org/W2962896155","https://openalex.org/W2962974533","https://openalex.org/W2963035245","https://openalex.org/W2963539064","https://openalex.org/W2970006822","https://openalex.org/W2972667718","https://openalex.org/W3015959238","https://openalex.org/W3034420534","https://openalex.org/W3100696337","https://openalex.org/W4289299319","https://openalex.org/W4293398859","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W894828327","https://openalex.org/W2136559180","https://openalex.org/W2216505304","https://openalex.org/W2188424442","https://openalex.org/W2381350675","https://openalex.org/W1614028504","https://openalex.org/W1996938627","https://openalex.org/W1994396704"],"abstract_inverted_index":{"Non-parallel":[0],"voice":[1],"conversion":[2,59,68],"(VC)":[3],"is":[4,158],"a":[5,17,67],"technique":[6],"for":[7,50,57,151],"learning":[8],"mappings":[9],"between":[10],"source":[11,133],"and":[12,24,33,120,139,147,173],"target":[13],"speeches":[14],"without":[15],"using":[16],"parallel":[18],"corpus.Recently,":[19],"cycle-consistent":[20],"adversarial":[21],"network":[22],"(CycleGAN)-VC":[23],"CycleGAN-VC2":[25,107],"have":[26,34],"shown":[27],"promising":[28],"results":[29],"regarding":[30],"this":[31],"problem":[32],"been":[35],"widely":[36],"used":[37,56],"as":[38,66],"benchmark":[39],"methods.However,":[40],"owing":[41],"to":[42,78,171,176],"the":[43,46,74,90,118,123,128,132,161,174],"ambiguity":[44],"of":[45,48,76,106,122,131,145,164,167],"effectiveness":[47],"CycleGAN-VC/VC2":[49,77],"mel-spectrogram":[51,65,79],"conversion,":[52],"they":[53],"are":[54],"typically":[55],"mel-cepstrum":[58,172],"even":[60],"when":[61],"comparative":[62],"methods":[63],"employ":[64],"target.To":[69],"address":[70],"this,":[71,100],"we":[72,83,101,115],"examined":[73],"applicability":[75],"conversion.Through":[80],"initial":[81],"experiments,":[82],"discovered":[84],"that":[85,93,108,150],"their":[86],"direct":[87],"applications":[88],"compromised":[89],"time-frequency":[91,110,129],"structure":[92,130],"should":[94],"be":[95],"preserved":[96],"during":[97],"conversion.To":[98],"remedy":[99],"propose":[102],"CycleGAN-VC3,":[103],"an":[104],"improvement":[105],"incorporates":[109],"adaptive":[111],"normalization":[112],"(TFAN).Using":[113],"TFAN,":[114],"can":[116],"adjust":[117],"scale":[119],"bias":[121],"converted":[124],"features":[125],"while":[126],"reflecting":[127],"mel-spectrogram.We":[134],"evaluated":[135],"CycleGAN-VC3":[136,155],"on":[137],"inter-gender":[138],"intra-gender":[140],"non-parallel":[141],"VC.A":[142],"subjective":[143],"evaluation":[144],"naturalness":[146],"similarity":[148],"showed":[149],"every":[152],"VC":[153],"pair,":[154],"outperforms":[156],"or":[157],"competitive":[159],"with":[160],"two":[162],"types":[163],"CycleGAN-VC2,":[165],"one":[166],"which":[168],"was":[169],"applied":[170],"other":[175],"mel-spectrogram.":[177],"1":[178]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-29T09:21:14.243279","created_date":"2025-10-10T00:00:00"}