{"id":"https://openalex.org/W3114104342","doi":"https://doi.org/10.1142/s0218126621501887","title":"High-Quality Many-to-Many Voice Conversion Using Transitive Star Generative Adversarial Networks with Adaptive Instance Normalization","display_name":"High-Quality Many-to-Many Voice Conversion Using Transitive Star Generative Adversarial Networks with Adaptive Instance Normalization","publication_year":2020,"publication_date":"2020-12-24","ids":{"openalex":"https://openalex.org/W3114104342","doi":"https://doi.org/10.1142/s0218126621501887","mag":"3114104342"},"language":"en","primary_location":{"id":"doi:10.1142/s0218126621501887","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218126621501887","pdf_url":null,"source":{"id":"https://openalex.org/S167602672","display_name":"Journal of Circuits Systems and Computers","issn_l":"0218-1266","issn":["0218-1266","1793-6454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Circuits, Systems and Computers","raw_type":"journal-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/A5100385632","display_name":"Yanping Li","orcid":"https://orcid.org/0000-0002-0074-7695"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanping Li","raw_affiliation_strings":["College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, P. R. China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102382549","display_name":"Zhengtao He","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao He","raw_affiliation_strings":["College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, P. R. China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100725798","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0002-5722-879X"},"institutions":[{"id":"https://openalex.org/I4210166603","display_name":"Jinling Institute of Technology","ror":"https://ror.org/05em1gq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166603"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["School of Software Engineering, Jinling Institute of Technology, Nanjing, Jiangsu, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Jinling Institute of Technology, Nanjing, Jiangsu, P. R. China","institution_ids":["https://openalex.org/I4210166603"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047980942","display_name":"Zhen Yang","orcid":"https://orcid.org/0000-0002-4400-3823"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Yang","raw_affiliation_strings":["College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, P. R. China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100385632"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.3911,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70256946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"30","issue":"10","first_page":"2150188","last_page":"2150188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9977999925613403,"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":0.995199978351593,"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/mean-opinion-score","display_name":"Mean opinion score","score":0.8341513276100159},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.802976667881012},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.774730384349823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.634409487247467},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5850390791893005},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5443451404571533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4150935709476471},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.41485533118247986},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3413427770137787}],"concepts":[{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.8341513276100159},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.802976667881012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774730384349823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.634409487247467},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5850390791893005},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5443451404571533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4150935709476471},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.41485533118247986},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3413427770137787},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218126621501887","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218126621501887","pdf_url":null,"source":{"id":"https://openalex.org/S167602672","display_name":"Journal of Circuits Systems and Computers","issn_l":"0218-1266","issn":["0218-1266","1793-6454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Circuits, Systems and Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G434885640","display_name":null,"funder_award_id":"61401227","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2011378162","https://openalex.org/W2071431631","https://openalex.org/W2111550316","https://openalex.org/W2121095010","https://openalex.org/W2123771434","https://openalex.org/W2135832479","https://openalex.org/W2161476805","https://openalex.org/W2290946177","https://openalex.org/W2471520273","https://openalex.org/W2475998840","https://openalex.org/W2517513811","https://openalex.org/W2603777577","https://openalex.org/W2889061305","https://openalex.org/W2892734764","https://openalex.org/W2898832121","https://openalex.org/W2902070858","https://openalex.org/W2911494248","https://openalex.org/W2947445680","https://openalex.org/W2963539064","https://openalex.org/W2964069186","https://openalex.org/W2972399707","https://openalex.org/W2972452545","https://openalex.org/W2972544500","https://openalex.org/W2972659941","https://openalex.org/W2972667718","https://openalex.org/W2973127257","https://openalex.org/W2973135352","https://openalex.org/W2982444549","https://openalex.org/W2996797022","https://openalex.org/W3002433751","https://openalex.org/W3006824058","https://openalex.org/W3100378519","https://openalex.org/W3102628737","https://openalex.org/W3105124182"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W172797710","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W4387098302","https://openalex.org/W169399214","https://openalex.org/W3100825170","https://openalex.org/W1935690276","https://openalex.org/W3158195778"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,108],"novel":[4],"high-quality":[5],"nonparallel":[6,119],"many-to-many":[7],"voice":[8],"conversion":[9],"method":[10,125,161],"based":[11],"on":[12],"transitive":[13],"star":[14],"generative":[15],"adversarial":[16],"networks":[17],"with":[18,23,32,42,118],"adaptive":[19],"instance":[20],"normalization":[21],"(Trans-StarGAN-VC":[22],"AdaIN).":[24],"First,":[25],"we":[26,87],"improve":[27],"the":[28,75,89,173],"structure":[29],"of":[30,38,77,101,139,155],"generator":[31,90],"TransNets":[33],"to":[34,58,67,91],"make":[35],"full":[36],"use":[37],"hierarchical":[39,51],"features":[40,52],"associated":[41],"speech":[43,72,99,131,177],"naturalness.":[44],"In":[45],"TransNets,":[46],"many":[47],"shortcut":[48],"connections":[49],"share":[50],"between":[53,175],"encoding":[54],"and":[55,62,73,115,133,144,150,168,170,178],"decoding":[56],"part":[57],"capture":[59],"sufficient":[60,93],"linguistic":[61],"semantic":[63],"information,":[64],"which":[65,105],"helps":[66],"provide":[68,163],"natural":[69],"sounding":[70],"converted":[71,176],"accelerate":[74],"convergence":[76],"training":[78,120],"process.":[79],"Second,":[80],"by":[81,148],"incorporating":[82],"AdaIN":[83],"for":[84,111],"style":[85],"transfer,":[86],"enable":[88],"learn":[92],"speaker":[94,134],"characteristic":[95],"information":[96],"directly":[97],"from":[98],"instead":[100],"using":[102],"attribute":[103],"labels,":[104],"also":[106,157],"provides":[107],"promising":[109],"framework":[110],"one-shot":[112],"VC.":[113],"Objective":[114],"subjective":[116],"experiments":[117],"data":[121],"show":[122],"that":[123,159],"our":[124,160],"significantly":[126],"outperforms":[127],"StarGAN-VC":[128],"in":[129],"both":[130],"naturalness":[132],"similarity.":[135],"The":[136,153],"mean":[137,140],"values":[138],"opinion":[141],"score":[142],"(MOS)":[143],"ABX":[145],"are":[146],"increased":[147],"24.5%":[149],"10.7%,":[151],"respectively.":[152],"comparison":[154],"spectrogram":[156],"shows":[158],"can":[162],"more":[164],"complete":[165],"harmonic":[166],"structures":[167],"details,":[169],"effectively":[171],"bridge":[172],"gap":[174],"target":[179],"speech.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}