{"id":"https://openalex.org/W4210729123","doi":"https://doi.org/10.1109/asru51503.2021.9687948","title":"Cyclegean: Cycle Generative Enhanced Adversarial Network for Voice Conversion","display_name":"Cyclegean: Cycle Generative Enhanced Adversarial Network for Voice Conversion","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210729123","doi":"https://doi.org/10.1109/asru51503.2021.9687948"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687948","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5028437800","display_name":"Xulong Zhang","orcid":"https://orcid.org/0000-0001-7005-992X"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xulong Zhang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Ping An Technology (Shenzhen) Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Ping An Technology (Shenzhen) Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977180","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0002-0988-5023"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Ping An Technology (Shenzhen) Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077957584","display_name":"Edward Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I2803097867","display_name":"Aquinas Institute of Theology","ror":"https://ror.org/029xxx628","country_code":"US","type":"education","lineage":["https://openalex.org/I2803097867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Xiao","raw_affiliation_strings":["Aquinas International Academy,USA","Aquinas International Academy, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aquinas International Academy,USA","institution_ids":["https://openalex.org/I2803097867"]},{"raw_affiliation_string":"Aquinas International Academy, USA","institution_ids":["https://openalex.org/I2803097867"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Ping An Technology (Shenzhen) Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"930","last_page":"937"},"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":0.9995999932289124,"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":0.9984999895095825,"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/discriminator","display_name":"Discriminator","score":0.8914618492126465},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.8286572098731995},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7913654446601868},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6611893773078918},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.6011781692504883},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5863267183303833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5431886911392212},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.543030858039856},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5028123259544373},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41344085335731506},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41127341985702515},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2549724876880646},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.066372811794281},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06313478946685791}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8914618492126465},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.8286572098731995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7913654446601868},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6611893773078918},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.6011781692504883},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5863267183303833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5431886911392212},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.543030858039856},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5028123259544373},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41344085335731506},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41127341985702515},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2549724876880646},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.066372811794281},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06313478946685791},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9687948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687948","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G6545684677","display_name":null,"funder_award_id":"2018YFB0204403,20I7YFB1401202,2018YFB1003500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1882958252","https://openalex.org/W1974932908","https://openalex.org/W2017425464","https://openalex.org/W2046056978","https://openalex.org/W2086796102","https://openalex.org/W2116593694","https://openalex.org/W2117676474","https://openalex.org/W2120605154","https://openalex.org/W2140345199","https://openalex.org/W2150769028","https://openalex.org/W2156142001","https://openalex.org/W2406026380","https://openalex.org/W2518172956","https://openalex.org/W2532494225","https://openalex.org/W2765811365","https://openalex.org/W2804998325","https://openalex.org/W2888922217","https://openalex.org/W2890964092","https://openalex.org/W2902070858","https://openalex.org/W2922104641","https://openalex.org/W2937579788","https://openalex.org/W2939131199","https://openalex.org/W2943899226","https://openalex.org/W2962793481","https://openalex.org/W2962896155","https://openalex.org/W2963035245","https://openalex.org/W2964135678","https://openalex.org/W2972399707","https://openalex.org/W2972849140","https://openalex.org/W2989985842","https://openalex.org/W2996414377","https://openalex.org/W3015434413","https://openalex.org/W3096831136","https://openalex.org/W3096864844","https://openalex.org/W3097692357","https://openalex.org/W3100696337","https://openalex.org/W3101689408","https://openalex.org/W6639480849","https://openalex.org/W6726528559","https://openalex.org/W6728445508","https://openalex.org/W6737196085"],"related_works":["https://openalex.org/W2995777218","https://openalex.org/W3217069185","https://openalex.org/W3049340819","https://openalex.org/W4308928038","https://openalex.org/W4200430540","https://openalex.org/W3141413246","https://openalex.org/W2888032422","https://openalex.org/W2808862658","https://openalex.org/W4322709305","https://openalex.org/W2996316059"],"abstract_inverted_index":{"Cycle":[0,68],"Generative":[1,69],"Adversarial":[2,71],"Network":[3,72],"(CycleGAN)":[4],"for":[5,121,142],"voice":[6,18,39,100],"conversion":[7],"(VC)":[8],"task":[9],"only":[10],"used":[11,130],"discriminators":[12,81],"to":[13,43,55,59,76,82,92,153],"identify":[14,93],"whether":[15,94],"the":[16,25,30,33,37,44,57,78,95,98,104,108,135,138,149,170],"input":[17,99],"is":[19,134,140],"generated":[20,38],"or":[21,101],"real.":[22],"It":[23],"means":[24],"confrontational":[26],"does":[27],"not":[28,40],"check":[29],"similarity":[31,61],"with":[32,118],"target":[34,60,83,89,96,122],"voice,":[35],"leading":[36],"much":[41],"similar":[42],"target.":[45],"In":[46,147],"this":[47,65],"paper,":[48],"instead":[49],"of":[50,160,167],"vocal":[51],"checking,":[52],"we":[53,112,129],"propose":[54],"enhance":[56],"confrontation":[58],"checking":[62],"that":[63],"addresses":[64],"problem.":[66],"A":[67],"Enhanced":[70],"(CycleGEAN)":[73],"was":[74],"introduced":[75],"make":[77],"original":[79],"two":[80],"classifier":[84,90,106],"and":[85,123,137,162],"non-target":[86,105,109],"classifier.":[87],"The":[88],"aims":[91],"speaks":[97],"not.":[102],"Similarly,":[103],"identifies":[107],"voice.":[110],"Furthermore,":[111],"add":[113],"a":[114],"gradient":[115],"reversal":[116],"layer":[117],"different":[119],"operations":[120],"non-target.":[124],"Then":[125],"in":[126,144],"each":[127],"GAN,":[128],"both":[131],"classifiers.":[132],"One":[133],"discriminator,":[136],"other":[139],"trained":[141],"using":[143],"another":[145],"GAN.":[146],"experiments,":[148],"proposed":[150],"method":[151],"compare":[152],"CycleGAN":[154],"improves":[155],"Mean":[156],"Opinion":[157],"Score":[158,165],"(MOS)":[159],"0.1":[161],"Voice":[163,171],"Similarity":[164],"(VSS)":[166],"0.2":[168],"on":[169],"Conversion":[172],"Challenge":[173],"2018":[174],"(VCC2018)":[175],"dataset.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}