{"id":"https://openalex.org/W4285345683","doi":"https://doi.org/10.1145/3474085.3475437","title":"Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus","display_name":"Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W4285345683","doi":"https://doi.org/10.1145/3474085.3475437"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475437","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5011787904","display_name":"Rongjie Huang","orcid":"https://orcid.org/0000-0002-1695-9000"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060844215","display_name":"Feiyang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyang Chen","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088179161","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0001-9889-5460"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065126806","display_name":"Jinglin Liu","orcid":"https://orcid.org/0000-0002-9905-3887"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinglin Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012657658","display_name":"Chenye Cui","orcid":"https://orcid.org/0009-0009-9083-1628"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenye Cui","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011787904"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":8.3098,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.98396081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3945","last_page":"3954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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":0.9886999726295471,"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":0.8804728984832764},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7527502775192261},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7368658781051636},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.48663291335105896},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4843248128890991},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.45179107785224915},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.4403282403945923},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.41191643476486206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4032019376754761},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12075266242027283},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09313732385635376}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8804728984832764},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527502775192261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7368658781051636},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.48663291335105896},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4843248128890991},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.45179107785224915},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.4403282403945923},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.41191643476486206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4032019376754761},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12075266242027283},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09313732385635376},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475437","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6000000238418579,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2067709094","https://openalex.org/W2124539664","https://openalex.org/W2160473997","https://openalex.org/W2172065531","https://openalex.org/W2962788625","https://openalex.org/W2963073614","https://openalex.org/W2963300588","https://openalex.org/W3015338123","https://openalex.org/W3015516707","https://openalex.org/W3034586846","https://openalex.org/W3081279708","https://openalex.org/W3144035034"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W172797710","https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W1489300767","https://openalex.org/W2909357361","https://openalex.org/W4387098302"],"abstract_inverted_index":{"High-fidelity":[0],"multi-singer":[1,48,74,93,169,216],"singing":[2,13,33,59,64,76,186,217],"voice":[3,14,34,60,65,77,218],"synthesis":[4,35,219],"is":[5],"challenging":[6],"for":[7,31,168],"neural":[8],"vocoder":[9,94],"due":[10],"to":[11,106,115,139],"the":[12,38,68,82,122,141,147,175,207,215],"data":[15],"shortage,":[16],"limited":[17],"singer":[18,58,86,119,130,144,157,185],"generalization,":[19],"and":[20,40,50,111,117,133,179,192],"large":[21],"computational":[22],"cost.":[23],"Existing":[24],"open":[25],"corpora":[26],"could":[27],"not":[28],"meet":[29],"requirements":[30],"high-fidelity":[32],"because":[36],"of":[37,143,177],"scale":[39],"quality":[41,193],"weaknesses.":[42],"Previous":[43],"vocoders":[44],"have":[45],"difficulty":[46,83],"in":[47,67,84,146,150,166,189,214],"modeling,":[49,87],"a":[51,72,91,103,129],"distinct":[52],"degradation":[53],"emerges":[54],"when":[55],"conducting":[56],"unseen":[57,85,184],"generation.":[61],"To":[62,80],"accelerate":[63],"researches":[66],"community,":[69],"we":[70,88,153],"release":[71],"large-scale,":[73],"Chinese":[75],"dataset":[78],"OpenSinger.":[79],"tackle":[81],"propose":[89,154],"Multi-Singer,":[90],"fast":[92],"with":[95,203],"generative":[96],"adversarial":[97,135],"networks.":[98],"Specifically,":[99],"1)":[100],"Multi-Singer":[101,127,182,210],"uses":[102],"multi-band":[104],"generator":[105],"speed":[107,191],"up":[108],"both":[109,190],"training":[110,136,162],"inference":[112],"procedure.":[113],"2)":[114],"capture":[116],"rebuild":[118],"identity":[120,145],"from":[121],"acoustic":[123,208],"feature":[124],"(i.e.,":[125],"mel-spectrogram),":[126],"adopts":[128],"conditional":[131,134],"discriminator":[132],"objective.":[137],"3)":[138],"supervise":[140],"reconstruction":[142],"spectrum":[148],"envelopes":[149],"frequency":[151],"domain,":[152],"an":[155],"auxiliary":[156],"perceptual":[158],"loss.":[159],"The":[160,197],"joint":[161],"approach":[163],"effectively":[164],"works":[165],"GANs":[167],"voices":[170,187],"modeling.":[171],"Experimental":[172],"results":[173],"verify":[174],"effectiveness":[176],"OpenSinger":[178],"show":[180],"that":[181,201],"improves":[183],"modeling":[188],"over":[194],"previous":[195],"methods.":[196],"further":[198],"experiment":[199],"proves":[200],"combined":[202],"FastSpeech":[204],"2":[205],"as":[206],"model,":[209],"achieves":[211],"strong":[212],"robustness":[213],"pipeline.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":10}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}