{"id":"https://openalex.org/W3187128306","doi":"https://doi.org/10.1109/taslp.2021.3104165","title":"Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System","display_name":"Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3187128306","doi":"https://doi.org/10.1109/taslp.2021.3104165","mag":"3187128306"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3104165","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3104165","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09511835.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09511835.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yukiya Hono","orcid":"https://orcid.org/0000-0003-1245-8791"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukiya Hono","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1245-8791","affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kei Hashimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Hashimoto","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Keiichiro Oura","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichiro Oura","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":null,"display_name":"Keiichi Tokuda","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":3.2756,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.93171076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"2803","last_page":"2815"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5083000063896179,"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":0.5083000063896179,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.12219999730587006,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10863","display_name":"Voice and Speech Disorders","score":0.09390000253915787,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.941100001335144},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.9409999847412109},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5217999815940857},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5026000142097473},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.4781999886035919},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43149998784065247},{"id":"https://openalex.org/keywords/musical-tone","display_name":"Musical tone","score":0.399399995803833},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.941100001335144},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.9409999847412109},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7469000220298767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6917999982833862},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5217999815940857},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5026000142097473},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.4781999886035919},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C86011254","wikidata":"https://www.wikidata.org/wiki/Q2717062","display_name":"Musical tone","level":4,"score":0.399399995803833},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3192000091075897},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C178992907","wikidata":"https://www.wikidata.org/wiki/Q1806413","display_name":"Electroglottograph","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2538999915122986}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3104165","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3104165","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09511835.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2108.02776","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.02776","pdf_url":"https://arxiv.org/pdf/2108.02776","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/taslp.2021.3104165","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3104165","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09511835.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2165465563","display_name":"A next-generation speech synthesis technology based on integration of hierarchical generative models and multi-task deep learning","funder_award_id":"19H04136","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6299358200","display_name":"PRISM: Speech privacy preservation based on selecting masking","funder_award_id":"18H04112","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6646335949","display_name":null,"funder_award_id":"JP18K11163","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320323523","display_name":"Casio Science Promotion Foundation","ror":"https://ror.org/0417n8r23"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3187128306.pdf","grobid_xml":"https://content.openalex.org/works/W3187128306.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W79324828","https://openalex.org/W2066598518","https://openalex.org/W2106792148","https://openalex.org/W2134973740","https://openalex.org/W2154920538","https://openalex.org/W2157412983","https://openalex.org/W2160815625","https://openalex.org/W2166823384","https://openalex.org/W2399853303","https://openalex.org/W2403471241","https://openalex.org/W2471520273","https://openalex.org/W2515336442","https://openalex.org/W2516406502","https://openalex.org/W2524467597","https://openalex.org/W2595110011","https://openalex.org/W2778460379","https://openalex.org/W2889244839","https://openalex.org/W2921576841","https://openalex.org/W2940405045","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972910332","https://openalex.org/W2973046048","https://openalex.org/W3015437531","https://openalex.org/W3015499232","https://openalex.org/W3081279708","https://openalex.org/W3096437652","https://openalex.org/W4395961138","https://openalex.org/W6601203246","https://openalex.org/W6604170644","https://openalex.org/W6604464690","https://openalex.org/W6631190155","https://openalex.org/W6634817459","https://openalex.org/W6638667902","https://openalex.org/W6675380101","https://openalex.org/W6678318511","https://openalex.org/W6696843773","https://openalex.org/W6713876852","https://openalex.org/W6776400185","https://openalex.org/W6779912715","https://openalex.org/W6783382068","https://openalex.org/W6784874479","https://openalex.org/W6790899109","https://openalex.org/W7061576544"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"Sinsy,":[3],"a":[4,46,56,88,91,98,117,144,158,195],"deep":[5],"neural":[6,146],"network":[7],"(DNN)-based":[8],"singing":[9,47,61,101,110,118,160,175,196],"voice":[10,48,161,197],"synthesis":[11],"(SVS)":[12],"system.":[13],"In":[14,139],"recent":[15],"years,":[16],"DNNs":[17],"have":[18,30],"been":[19],"utilized":[20],"in":[21,215],"statistical":[22],"parametric":[23],"SVS":[24,28,40,172],"systems,":[25],"and":[26,51,74,97,100,129,131,204,207],"DNN-based":[27,171],"systems":[29,41,155],"demonstrated":[31],"better":[32,115,132,199,211],"performance":[33],"than":[34],"conventional":[35],"hidden":[36],"Markov":[37],"model-based":[38],"ones.":[39],"are":[42,64],"required":[43],"to":[44,126,156,173],"synthesize":[45,174,194],"with":[49,148,177,198],"pitch":[50,128,167,179],"timing":[52,75],"that":[53,63],"strictly":[54],"follow":[55],"given":[57],"musical":[58,69],"score.":[59],"Additionally,":[60],"expressions":[62],"not":[65],"described":[66],"on":[67],"the":[68,120,136,151,182],"score,":[70],"such":[71],"as":[72],"vibrato":[73,130],"fluctuations,":[76],"should":[77],"be":[78,104],"reproduced.":[79],"The":[80],"proposed":[81,121],"system":[82,122,192],"is":[83],"composed":[84],"of":[85,109],"four":[86],"modules:":[87],"time-lag":[89],"model,":[90,93,96],"duration":[92],"an":[94],"acoustic":[95,137],"vocoder,":[99],"voices":[102,111,176],"can":[103,193,209],"synthesized":[105],"taking":[106],"these":[107],"characteristics":[108],"into":[112,135,153],"account.":[113],"To":[114],"model":[116],"voice,":[119],"incorporates":[123],"improved":[124],"approaches":[125],"modeling":[127],"training":[133,183],"criteria":[134],"model.":[138],"addition,":[140],"we":[141,164],"incorporated":[142],"PeriodNet,":[143],"non-autoregressive":[145],"vocoder":[147],"robustness":[149],"for":[150,170],"pitch,":[152,206],"our":[154,191],"generate":[157],"high-fidelity":[159],"waveform.":[162],"Moreover,":[163],"propose":[165],"automatic":[166],"correction":[168],"techniques":[169],"correct":[178,205],"even":[180],"if":[181],"data":[184],"has":[185],"out-of-tune":[186],"phrases.":[187],"Experimental":[188],"results":[189],"show":[190],"timing,":[200],"more":[201],"natural":[202],"vibrato,":[203],"it":[208],"achieve":[210],"mean":[212],"opinion":[213],"scores":[214],"subjective":[216],"evaluation":[217],"tests.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-08-16T00:00:00"}