{"id":"https://openalex.org/W4224920040","doi":"https://doi.org/10.1109/icassp43922.2022.9746992","title":"U-GAT-VC: Unsupervised Generative Attentional Networks for Non-Parallel Voice Conversion","display_name":"U-GAT-VC: Unsupervised Generative Attentional Networks for Non-Parallel Voice Conversion","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920040","doi":"https://doi.org/10.1109/icassp43922.2022.9746992"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746992","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101461086","display_name":"Sheng Shi","orcid":"https://orcid.org/0009-0002-3573-8104"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]},{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Shi","raw_affiliation_strings":["Northwest University,Xi’an,P. R. China,710127","AI Lab, Lenovo Research, Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwest University,Xi’an,P. R. China,710127","institution_ids":["https://openalex.org/I37802460"]},{"raw_affiliation_string":"AI Lab, Lenovo Research, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083867853","display_name":"Jiahao Shao","orcid":"https://orcid.org/0009-0007-0409-4947"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Shao","raw_affiliation_strings":["Tsinghua University,Beijing,P. R. China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,P. R. China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102447219","display_name":"Yifei Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifei Hao","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,90007"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,90007","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069959549","display_name":"Yangzhou Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangzhou Du","raw_affiliation_strings":["Lenovo Research,AI Lab,Beijing,P. R. China,100094"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lenovo Research,AI Lab,Beijing,P. R. China,100094","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100728564","display_name":"Jianping Fan","orcid":"https://orcid.org/0000-0002-4923-0910"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]},{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Fan","raw_affiliation_strings":["Northwest University,Xi’an,P. R. China,710127","AI Lab, Lenovo Research, Beijing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwest University,Xi’an,P. R. China,710127","institution_ids":["https://openalex.org/I37802460"]},{"raw_affiliation_string":"AI Lab, Lenovo Research, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210156165"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6748,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68079844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7017","last_page":"7021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987999796867371,"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":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8201936483383179},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7794142961502075},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6349974274635315},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5767443180084229},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.551283597946167},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4894636869430542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4848974347114563},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47844886779785156},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45276251435279846},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4486454129219055},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3698403835296631},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36814722418785095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8201936483383179},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7794142961502075},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6349974274635315},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5767443180084229},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.551283597946167},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4894636869430542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4848974347114563},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47844886779785156},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45276251435279846},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4486454129219055},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3698403835296631},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36814722418785095},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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:10.1109/icassp43922.2022.9746992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746992","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2142300631","https://openalex.org/W2148846882","https://openalex.org/W2153057929","https://openalex.org/W2193413348","https://openalex.org/W2331128040","https://openalex.org/W2518312472","https://openalex.org/W2532494225","https://openalex.org/W2567070169","https://openalex.org/W2774848319","https://openalex.org/W2937579788","https://openalex.org/W2962793481","https://openalex.org/W2962960082","https://openalex.org/W2963035245","https://openalex.org/W2963539064","https://openalex.org/W2975414524","https://openalex.org/W2996286887","https://openalex.org/W2996414377","https://openalex.org/W3095936335","https://openalex.org/W3096356991","https://openalex.org/W3101689408","https://openalex.org/W6687566353","https://openalex.org/W6702130928","https://openalex.org/W6731370813","https://openalex.org/W6746801104","https://openalex.org/W6766150548"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4283803360","https://openalex.org/W4317695495","https://openalex.org/W4387506531"],"abstract_inverted_index":{"Non-parallel":[0],"voice":[1,9,62,103,143],"conversion":[2,104,140],"(VC)":[3],"is":[4,50],"a":[5,17,52,86,94],"technique":[6],"of":[7,67,139],"transfer-ring":[8],"from":[10],"one":[11],"style":[12],"to":[13,27,54,70,100,105,122],"another":[14],"without":[15],"using":[16,31],"parallel":[18],"corpus":[19],"in":[20,73,80,111,119,137],"model":[21,121,134],"training.":[22],"Various":[23],"methods":[24],"are":[25],"proposed":[26,133],"approach":[28],"non-parallel":[29],"VC":[30],"deep":[32],"neural":[33],"networks.":[34],"Among":[35],"them,":[36],"CycleGAN-VC":[37],"and":[38,60,63,97,128,142],"its":[39],"variants":[40],"have":[41],"been":[42],"widely":[43],"accepted":[44],"as":[45],"benchmark":[46],"methods.":[47],"However,":[48],"there":[49],"still":[51],"gap":[53],"bridge":[55],"between":[56],"the":[57,102],"real":[58],"target":[59],"converted":[61],"an":[64],"increased":[65],"number":[66],"parameters":[68],"leads":[69],"slow":[71],"convergence":[72],"training":[74],"process.":[75],"Inspired":[76],"by":[77],"recent":[78],"advancements":[79],"unsupervised":[81,89],"image":[82],"translation,":[83],"we":[84],"propose":[85],"new":[87],"end-to-end":[88],"framework":[90],"U-GAT-VC":[91],"that":[92],"adopts":[93],"novel":[95],"inter-":[96],"intra-attention":[98],"mechanism":[99],"guide":[101],"focus":[106],"on":[107],"more":[108],"important":[109],"regions":[110],"spectrograms.":[112],"We":[113],"also":[114],"introduce":[115],"disentangle":[116],"perceptual":[117],"loss":[118],"our":[120,132],"capture":[123],"high-level":[124],"spectral":[125],"features.":[126],"Subjective":[127],"objective":[129],"evaluations":[130],"shows":[131],"outperforms":[135],"CycleGAN-VC2/3":[136],"terms":[138],"quality":[141],"naturalness.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}