{"id":"https://openalex.org/W4298397573","doi":"https://doi.org/10.1145/3552466.3556534","title":"Singing-Tacotron","display_name":"Singing-Tacotron","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W4298397573","doi":"https://doi.org/10.1145/3552466.3556534"},"language":"en","primary_location":{"id":"doi:10.1145/3552466.3556534","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3552466.3556534","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3552466.3556534","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3552466.3556534","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100453420","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0001-8099-9704"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073918837","display_name":"Ruibo Fu","orcid":"https://orcid.org/0000-0001-9598-1881"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibo Fu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"59"},"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":0.9997000098228455,"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":0.9983000159263611,"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/duration","display_name":"Duration (music)","score":0.823810338973999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7999441623687744},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7274187207221985},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.6639736890792847},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6312453746795654},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6114723682403564},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5195437073707581},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5089747905731201},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48441603779792786},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4331849217414856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35117438435554504},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09435221552848816}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.823810338973999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7999441623687744},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7274187207221985},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.6639736890792847},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6312453746795654},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6114723682403564},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5195437073707581},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5089747905731201},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48441603779792786},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4331849217414856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35117438435554504},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09435221552848816},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3552466.3556534","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3552466.3556534","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3552466.3556534","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3552466.3556534","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3552466.3556534","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3552466.3556534","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5381013183","display_name":null,"funder_award_id":"61831022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7853071381","display_name":null,"funder_award_id":"62101553","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8374701036","display_name":null,"funder_award_id":"61901473","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G99649665","display_name":null,"funder_award_id":"No.61831022","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4298397573.pdf","grobid_xml":"https://content.openalex.org/works/W4298397573.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W2043003570","https://openalex.org/W2106560396","https://openalex.org/W2107860279","https://openalex.org/W2111284386","https://openalex.org/W2515336442","https://openalex.org/W2921576841","https://openalex.org/W2951310434","https://openalex.org/W2963091184","https://openalex.org/W2964243274","https://openalex.org/W3015499232","https://openalex.org/W3096437652","https://openalex.org/W3104557543","https://openalex.org/W3133525064","https://openalex.org/W3142087749"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W4310670065","https://openalex.org/W634160686","https://openalex.org/W2597614303","https://openalex.org/W2378183644","https://openalex.org/W2287414930","https://openalex.org/W2366944513"],"abstract_inverted_index":{"End-to-end":[0],"singing":[1,19],"voice":[2,20],"synthesis":[3],"(SVS)":[4],"is":[5,23,71,110,155],"attractive":[6],"due":[7],"to":[8,25,37,44,112,135,146,157,168],"the":[9,15,27,38,66,73,80,95,121,129,136,149,159,186,189,192,199],"avoidance":[10],"of":[11,18,116,177,188,194,201],"pre-aligned":[12],"data.":[13],"However,":[14],"auto-learned":[16],"alignment":[17,50],"with":[21],"lyrics":[22],"difficult":[24],"match":[26],"duration":[28,83,90,108,202],"information":[29,51],"in":[30],"a":[31,88,107,114,152],"musical":[32,81,122],"score,":[33],"which":[34],"will":[35],"lead":[36],"model":[39,160],"instability":[40],"or":[41,139],"even":[42],"failure":[43],"synthesize":[45],"voice.":[46],"To":[47],"learn":[48,113],"accurate":[49],"automatically,":[52],"this":[53],"paper":[54],"proposes":[55],"an":[56],"end-to-end":[57],"SVS":[58,96],"framework,":[59],"named":[60],"Singing-Tacotron.":[61],"The":[62,98],"main":[63],"difference":[64],"between":[65],"proposed":[67,111],"framework":[68],"and":[69,164,173,198],"Tacotron":[70],"that":[72],"speech":[74],"can":[75,101,127,179],"be":[76,180],"controlled":[77],"significantly":[78],"by":[79],"score's":[82],"information.":[84,171],"Firstly,":[85],"we":[86],"propose":[87],"global":[89,117,195],"control":[91,102,203],"attention":[92,99,130,167],"mechanism":[93,100,131],"for":[94],"model.":[97],"each":[103,142],"phoneme's":[104],"duration.":[105],"Secondly,":[106],"encoder":[109],"set":[115],"transition":[118,125,196],"tokens":[119,126,197],"from":[120],"score.":[123],"These":[124],"help":[128,158],"decide":[132],"whether":[133],"moving":[134],"next":[137],"phoneme":[138],"staying":[140],"at":[141,182],"decoding":[143],"step.":[144],"Thirdly,":[145],"further":[147],"improve":[148],"model's":[150],"stability,":[151],"dynamic":[153],"filter":[154],"designed":[156],"overcome":[161],"noise":[162],"interference":[163],"pay":[165],"more":[166],"local":[169],"context":[170],"Subjective":[172],"objective":[174],"evaluation":[175],"\\footnoteExamples":[176],"experiments":[178],"found":[181],"\\hrefhttps://hairuo55.github.io/SingingTacotron":[183],"https://hairuo55.github.io/SingingTacotron.":[184],"verify":[185],"effectiveness":[187],"method.":[190],"Furthermore,":[191],"role":[193],"effect":[200],"are":[204],"explored.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2022-10-02T00:00:00"}
