{"id":"https://openalex.org/W3207340675","doi":"https://doi.org/10.1109/icassp43922.2022.9747664","title":"VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis","display_name":"VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207340675","doi":"https://doi.org/10.1109/icassp43922.2022.9747664","mag":"3207340675"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747664","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":"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/A5060467975","display_name":"Yongmao Zhang","orcid":"https://orcid.org/0009-0000-0526-5778"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongmao Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064364353","display_name":"Jian Cong","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cong","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064426059","display_name":"Heyang Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heyang Xue","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066245750","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-9051-2111"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050166453","display_name":"Pengcheng Zhu","orcid":"https://orcid.org/0000-0001-9867-7041"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Zhu","raw_affiliation_strings":["NetEase Inc,Fuxi AI Lab,Hangzhou,China","Fuxi AI Lab, NetEase Inc, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Inc,Fuxi AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036369578","display_name":"Mengxiao Bi","orcid":"https://orcid.org/0009-0007-6680-481X"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxiao Bi","raw_affiliation_strings":["NetEase Inc,Fuxi AI Lab,Hangzhou,China","Fuxi AI Lab, NetEase Inc, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Inc,Fuxi AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7098,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.96925523,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7237","last_page":"7241"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8270111083984375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7571394443511963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7500556707382202},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5790436267852783},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5281978249549866},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47232168912887573},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.4451712369918823},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4362289309501648},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4186769723892212},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40757885575294495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37857598066329956},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15613225102424622}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8270111083984375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7571394443511963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7500556707382202},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5790436267852783},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5281978249549866},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47232168912887573},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.4451712369918823},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4362289309501648},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4186769723892212},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40757885575294495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37857598066329956},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15613225102424622},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747664","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":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2889244839","https://openalex.org/W2921576841","https://openalex.org/W2940405045","https://openalex.org/W2946200149","https://openalex.org/W2962695743","https://openalex.org/W2964307104","https://openalex.org/W2970730223","https://openalex.org/W3015499232","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3081279708","https://openalex.org/W3082910224","https://openalex.org/W3092028330","https://openalex.org/W3097152652","https://openalex.org/W3097514409","https://openalex.org/W3098403858","https://openalex.org/W3133525064","https://openalex.org/W3169905056","https://openalex.org/W3196760057","https://openalex.org/W3198869563","https://openalex.org/W4285719527","https://openalex.org/W4287761884","https://openalex.org/W4297798428","https://openalex.org/W4298580827","https://openalex.org/W6640963894","https://openalex.org/W6714644935","https://openalex.org/W6748409065","https://openalex.org/W6763832098","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6779912715","https://openalex.org/W6783382068","https://openalex.org/W6783867762","https://openalex.org/W6796464841"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W4380714744","https://openalex.org/W2387995142","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2964074194","https://openalex.org/W2057775761","https://openalex.org/W2985313479"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,84,112,135],"propose":[4],"VISinger,":[5],"a":[6,86,90,156],"complete":[7],"end-to-end":[8,33],"high-quality":[9],"singing":[10,18,127,133,151,159],"voice":[11],"synthesis":[12],"(SVS)":[13],"system":[14],"that":[15,162],"directly":[16],"generates":[17],"audio":[19],"from":[20],"lyrics":[21],"and":[22,49,79,89,99,169],"musical":[23],"score.":[24],"Our":[25],"approach":[26,168],"is":[27],"inspired":[28],"by":[29],"VITS":[30],"[1],":[31],"an":[32,115],"speech":[34],"generation":[35],"model":[36],"which":[37],"adopts":[38],"VAE-based":[39],"posterior":[40],"encoder":[41,48,66],"augmented":[42],"with":[43,150],"normalizing":[44],"flow":[45],"based":[46],"prior":[47,65,92,122],"adversarial":[50],"decoder.":[51],"VISinger":[52,163],"follows":[53],"the":[54,64,69,96,105,120,132,137,143,170,176],"main":[55],"architecture":[56],"of":[57,71,75,81,178],"VITS,":[58],"but":[59],"makes":[60],"substantial":[61],"improvements":[62],"to":[63,68,94,118,125,130,140,145],"according":[67],"characteristics":[70],"singing.":[72,110],"First,":[73],"instead":[74],"using":[76],"phoneme-level":[77],"mean":[78,98],"variance":[80,100],"acoustic":[82,102,107],"features,":[83,103],"introduce":[85,114],"length":[87],"regulator":[88],"frame":[91,121],"network":[93],"get":[95],"frame-level":[97],"on":[101,155],"modeling":[104],"rich":[106],"variation":[108],"in":[109],"Second,":[111],"further":[113],"F0":[116],"predictor":[117,139],"guide":[119],"network,":[123],"leading":[124],"stabler":[126],"performance.":[128],"Finally,":[129],"improve":[131],"rhythm,":[134],"modify":[136],"duration":[138,147],"specifically":[141],"predict":[142],"phoneme":[144],"note":[146,152],"ratio,":[148],"helped":[149],"normalization.":[153],"Experiments":[154],"professional":[157],"Mandarin":[158],"corpus":[160],"show":[161],"significantly":[164],"outperforms":[165],"FastSpeech+Neural-Vocoder":[166],"two-stage":[167],"oracle":[171],"VITS;":[172],"ablation":[173],"study":[174],"demonstrates":[175],"effectiveness":[177],"different":[179],"contributions.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}