{"id":"https://openalex.org/W4387968499","doi":"https://doi.org/10.1145/3581783.3612150","title":"UniSinger: Unified End-to-End Singing Voice Synthesis With Cross-Modality Information Matching","display_name":"UniSinger: Unified End-to-End Singing Voice Synthesis With Cross-Modality Information Matching","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968499","doi":"https://doi.org/10.1145/3581783.3612150"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612150","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5016467822","display_name":"Zhiqing Hong","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":"Zhiqing Hong","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0907-6621","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, 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, China"],"raw_orcid":"https://orcid.org/0009-0009-9083-1628","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","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":false,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1695-9000","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067136900","display_name":"Lichao Zhang","orcid":"https://orcid.org/0009-0009-0389-4090"},"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":"Lichao Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-0389-4090","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086279968","display_name":"Jinglin Liu","orcid":"https://orcid.org/0000-0003-4420-4163"},"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, China"],"raw_orcid":"https://orcid.org/0000-0003-4420-4163","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043581249","display_name":"Jinzheng He","orcid":"https://orcid.org/0009-0003-3024-9624"},"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":"Jinzheng He","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-3024-9624","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, 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, China"],"raw_orcid":"https://orcid.org/0000-0001-6121-0384","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.3226,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65846179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7569","last_page":"7579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.9965000152587891,"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":0.8623156547546387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8019523620605469},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7375657558441162},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6184919476509094},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4577350616455078},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4257696270942688},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4153260588645935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3351514935493469},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08869573473930359}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8623156547546387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019523620605469},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7375657558441162},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6184919476509094},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4577350616455078},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4257696270942688},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4153260588645935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3351514935493469},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08869573473930359},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612150","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6050241676","display_name":"\u57fa\u4e8e\u5f31\u6807\u6ce8\u7684\u8de8\u6a21\u6001\u89c6\u9891\u5b9a\u4f4d\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072397","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7528510259","display_name":"\u57fa\u4e8e\u5927\u89c4\u6a21\u8de8\u5a92\u4f53\u77e5\u8bc6\u7f51\u7edc\u7684\u590d\u6742\u89c6\u9891\u95ee\u7b54\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61836002","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2593768305","https://openalex.org/W2902070858","https://openalex.org/W2903739847","https://openalex.org/W2963539064","https://openalex.org/W2964243274","https://openalex.org/W3016007107","https://openalex.org/W3036167779","https://openalex.org/W3081279708","https://openalex.org/W3092028330","https://openalex.org/W3096831136","https://openalex.org/W3133525064","https://openalex.org/W3158762648","https://openalex.org/W3206191467","https://openalex.org/W3207340675","https://openalex.org/W4285345683","https://openalex.org/W6632668414","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2406877384","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2595839522","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W4288088492","https://openalex.org/W2982290989"],"abstract_inverted_index":{"Though":[0],"previous":[1],"works":[2],"have":[3],"shown":[4],"remarkable":[5],"achievements":[6],"in":[7,144,165,178],"singing":[8,26,69,78,81,85,90,109],"voice":[9,27,70,79,82,86,91],"generation,":[10],"most":[11,44],"existing":[12],"models":[13],"focus":[14],"on":[15,134],"one":[16,41],"specific":[17],"application":[18],"and":[19,53,89,127,156,170],"there":[20],"is":[21],"a":[22,66,95,114],"lack":[23],"of":[24,42,107,153],"unified":[25,67],"synthesis":[28,83],"models.":[29],"In":[30,60],"addition":[31],"to":[32,77,119],"low":[33],"relevance":[34],"among":[35],"tasks,":[36],"different":[37,105],"input":[38],"modalities":[39],"are":[40],"the":[43,108,121,135,151],"intractable":[45],"hindrances.":[46],"Current":[47],"methods":[48],"suffer":[49],"from":[50],"information":[51,116,157],"confusion":[52],"they":[54],"can":[55,175],"not":[56],"perform":[57,100],"precise":[58],"control.":[59],"this":[61],"work,":[62],"we":[63,99],"propose":[64,113],"UniSinger,":[65],"end-to-end":[68,129],"synthesizer,":[71],"which":[72],"integrates":[73],"three":[74,145],"abilities":[75],"related":[76],"generation:":[80],"(SVS),":[84],"conversion":[87],"(SVC),":[88],"editing":[92],"(SVE)":[93],"into":[94],"single":[96],"framework.":[97],"Specifically,":[98],"representation":[101,154],"disentanglement":[102,155],"for":[103],"controlling":[104],"attributes":[106],"voice.":[110],"We":[111],"further":[112],"cross-modality":[115],"matching":[117],"method":[118],"close":[120],"distribution":[122],"gap":[123],"between":[124],"multi-modal":[125],"inputs":[126],"achieve":[128],"training.":[130],"The":[131],"experiments":[132,149],"conducted":[133],"OpenSinger":[136],"dataset":[137],"demonstrate":[138],"that":[139,160],"UniSinger":[140,161],"achieves":[141],"state-of-the-art":[142],"results":[143],"applications.":[146],"Further":[147],"extensive":[148],"verify":[150],"capability":[152],"matching,":[158],"reflecting":[159],"enjoys":[162],"great":[163],"superiority":[164],"sample":[166],"quality,":[167],"timbre":[168],"similarity,":[169],"multi-task":[171],"compatibility.":[172],"Audio":[173],"samples":[174],"be":[176],"found":[177],"https://unisinger.github.io/Samples/.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
