{"id":"https://openalex.org/W4372190416","doi":"https://doi.org/10.1109/icassp49357.2023.10095102","title":"WeSinger 2: Fully Parallel Singing Voice Synthesis via Multi-Singer Conditional Adversarial Training","display_name":"WeSinger 2: Fully Parallel Singing Voice Synthesis via Multi-Singer Conditional Adversarial Training","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372190416","doi":"https://doi.org/10.1109/icassp49357.2023.10095102"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5048848376","display_name":"Zewang Zhang","orcid":"https://orcid.org/0009-0001-3620-8706"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zewang Zhang","raw_affiliation_strings":["Tencent Inc,China","Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101398585","display_name":"Yibin Zheng","orcid":"https://orcid.org/0000-0001-9158-1813"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibin Zheng","raw_affiliation_strings":["Tencent Inc,China","Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701664","display_name":"Xinhui Li","orcid":"https://orcid.org/0000-0003-0164-3422"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhui Li","raw_affiliation_strings":["Tencent Inc,China","Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658678","display_name":"Li L\u00fc","orcid":"https://orcid.org/0000-0001-5230-3749"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Lu","raw_affiliation_strings":["Tencent Inc,China","Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":2.175,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90428772,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9994999766349792,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8453288078308105},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7680772542953491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7633599042892456},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6765967011451721},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.480175644159317},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4737478196620941},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.46999868750572205},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45213618874549866},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.41483357548713684},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.412431925535202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37689095735549927},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1560608148574829},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07242026925086975}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8453288078308105},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7680772542953491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633599042892456},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6765967011451721},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.480175644159317},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4737478196620941},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.46999868750572205},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45213618874549866},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41483357548713684},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.412431925535202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37689095735549927},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1560608148574829},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07242026925086975},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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:10.1109/icassp49357.2023.10095102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2066598518","https://openalex.org/W2091425152","https://openalex.org/W2516406502","https://openalex.org/W2593414223","https://openalex.org/W2889244839","https://openalex.org/W2940405045","https://openalex.org/W2963091184","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972910332","https://openalex.org/W2984106626","https://openalex.org/W3015338123","https://openalex.org/W3015516707","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3095074555","https://openalex.org/W3097514409","https://openalex.org/W3133525064","https://openalex.org/W3144035034","https://openalex.org/W3196760057","https://openalex.org/W3197481261","https://openalex.org/W3206191467","https://openalex.org/W3207340675","https://openalex.org/W4221167708","https://openalex.org/W4224917388","https://openalex.org/W4285345683","https://openalex.org/W4296068763","https://openalex.org/W4320013936","https://openalex.org/W6748409065","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2502115930","https://openalex.org/W3127543252","https://openalex.org/W2065606036"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"to":[3,12,39,137,157,159],"introduce":[4],"a":[5,138],"robust":[6],"singing":[7,18,125,131],"voice":[8],"synthesis":[9],"(SVS)":[10],"system":[11,121],"produce":[13,123],"very":[14],"natural":[15],"and":[16,53,97,108],"realistic":[17],"voices":[19,126],"efficiently":[20,127],"by":[21,128],"leveraging":[22],"the":[23,42,49,55,60,66,69,75,78,86,94,102],"adversarial":[24,90],"training":[25],"strategy.":[26],"On":[27,59],"one":[28],"hand,":[29,62],"we":[30,63,153],"designed":[31],"simple":[32],"but":[33],"generic":[34],"random":[35],"area":[36],"conditional":[37,91],"discriminators":[38,92],"help":[40,87],"supervise":[41],"acoustic":[43],"model,":[44],"which":[45,81],"can":[46,122],"effectively":[47],"avoid":[48],"over-smoothed":[50],"spectrogram":[51,67],"prediction":[52],"improve":[54],"expressiveness":[56],"of":[57,88,144],"SVS.":[58],"other":[61],"subtly":[64],"combined":[65],"with":[68,85,114,147],"frame-level":[70],"linearly-interpolated":[71],"F0":[72],"sequence":[73],"as":[74],"input":[76],"for":[77],"neural":[79],"vocoder,":[80],"is":[82],"then":[83],"optimized":[84],"multiple":[89],"in":[93,101],"waveform":[95],"domain":[96],"multi-scale":[98],"distance":[99],"functions":[100],"frequency":[103],"do-main.":[104],"The":[105],"experimental":[106],"results":[107],"ablation":[109],"studies":[110],"concluded":[111],"that,":[112],"compared":[113],"our":[115,119],"previous":[116],"auto-regressive":[117],"work,":[118],"new":[120],"high-quality":[124],"fine-tuning":[129],"different":[130,148],"datasets":[132],"covering":[133],"from":[134],"several":[135],"minutes":[136],"few":[139],"hours.":[140],"A":[141],"large":[142],"number":[143],"synthesized":[145],"songs":[146],"timbres":[149],"are":[150],"available":[151],"online1and":[152],"highly":[154],"recommend":[155],"readers":[156],"listen":[158],"them.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
