{"id":"https://openalex.org/W2921576841","doi":"https://doi.org/10.23919/apsipa.2018.8659797","title":"Recent Development of the DNN-based Singing Voice Synthesis System \u2014 Sinsy","display_name":"Recent Development of the DNN-based Singing Voice Synthesis System \u2014 Sinsy","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921576841","doi":"https://doi.org/10.23919/apsipa.2018.8659797","mag":"2921576841"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659797","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5086910479","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":true,"raw_author_name":"Yukiya Hono","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079903149","display_name":"Shumma Murata","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":"Shumma Murata","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016084389","display_name":"Kazuhiro Nakamura","orcid":"https://orcid.org/0000-0002-6095-8996"},"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":"Kazuhiro Nakamura","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067594810","display_name":"Kei Hashimoto","orcid":"https://orcid.org/0000-0003-2081-0396"},"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":["Department of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049909008","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":["Department of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","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":["Department of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"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":["Department of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5086910479"],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":4.0721,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.95182313,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1003","last_page":"1009"},"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":0.9941999912261963,"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":0.9066004753112793},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.7748793363571167},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.759701132774353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7451329231262207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7263097763061523},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5965465307235718},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5851638913154602},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14568805694580078}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9066004753112793},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.7748793363571167},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.759701132774353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7451329231262207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7263097763061523},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5965465307235718},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5851638913154602},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14568805694580078},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.23919/apsipa.2018.8659797","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W80543058","https://openalex.org/W1579853615","https://openalex.org/W1963627370","https://openalex.org/W1979449467","https://openalex.org/W1984905644","https://openalex.org/W2049686551","https://openalex.org/W2102003408","https://openalex.org/W2106792148","https://openalex.org/W2111284386","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2136507169","https://openalex.org/W2154920538","https://openalex.org/W2160815625","https://openalex.org/W2166823384","https://openalex.org/W2228674556","https://openalex.org/W2402539796","https://openalex.org/W2403471241","https://openalex.org/W2408435475","https://openalex.org/W2515336442","https://openalex.org/W2519091744","https://openalex.org/W2591927543","https://openalex.org/W2778460379","https://openalex.org/W2949382160","https://openalex.org/W6601203246","https://openalex.org/W6603264027","https://openalex.org/W6674021436","https://openalex.org/W6675380101","https://openalex.org/W6713876852"],"related_works":["https://openalex.org/W2373880408","https://openalex.org/W405661683","https://openalex.org/W2532856746","https://openalex.org/W238390473","https://openalex.org/W2119168266","https://openalex.org/W2978145617","https://openalex.org/W2108382268","https://openalex.org/W4230480656","https://openalex.org/W3149963859","https://openalex.org/W4391272374"],"abstract_inverted_index":{"This":[0],"paper":[1,102],"describes":[2,103],"a":[3,63,67],"singing":[4,33,51,73,82,111],"voice":[5,17,34,74,112],"synthesis":[6,18,35,75],"system":[7,76],"based":[8,20,37],"on":[9,21,38],"deep":[10],"neural":[11],"networks":[12],"(DNNs)":[13],"named":[14],"Sinsy.":[15],"Singing":[16],"systems":[19,36,90],"hidden":[22],"Markov":[23],"models":[24],"(HMMs)":[25],"have":[26,40],"grown":[27],"in":[28],"the":[29,46,49,71,79,88,95,100,104,107],"last":[30],"decade.":[31],"Recently,":[32],"DNNs":[39],"been":[41],"proposed.":[42],"It":[43],"has":[44],"improved":[45],"naturalness":[47],"of":[48,106],"synthesized":[50],"voices.":[52,83],"In":[53,98],"this":[54],"paper,":[55],"we":[56],"introduce":[57],"several":[58],"techniques,":[59],"i.e.,":[60],"trajectory":[61],"training,":[62],"vibrato":[64],"model,":[65,69],"and":[66],"time-lag":[68],"into":[70],"DNN-based":[72,89],"to":[77],"synthesize":[78],"high":[80],"quality":[81],"Experimental":[84],"results":[85],"show":[86],"that":[87],"with":[91],"these":[92],"techniques":[93],"outperformed":[94],"HMM-based":[96],"systems.":[97],"addition,":[99],"present":[101],"details":[105],"on-line":[108],"service":[109],"for":[110],"synthesis.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}