{"id":"https://openalex.org/W4372260026","doi":"https://doi.org/10.1109/icassp49357.2023.10096239","title":"NNSVS: A Neural Network-Based Singing Voice Synthesis Toolkit","display_name":"NNSVS: A Neural Network-Based Singing Voice Synthesis Toolkit","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260026","doi":"https://doi.org/10.1109/icassp49357.2023.10096239"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100669485","display_name":"Ryuichi Yamamoto","orcid":"https://orcid.org/0000-0003-0299-5470"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I4210154963","display_name":"Lintec Corporation (Japan)","ror":"https://ror.org/04qrdn471","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210154963"]},{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuichi Yamamoto","raw_affiliation_strings":["LINE Corp.,Japan","LINE Corp., Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corp.,Japan","institution_ids":["https://openalex.org/I4210096607","https://openalex.org/I4210154963"]},{"raw_affiliation_string":"LINE Corp., Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066881979","display_name":"Reo Yoneyama","orcid":"https://orcid.org/0000-0001-9686-4783"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Reo Yoneyama","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006808971","display_name":"Tomoki Toda","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.883728563785553},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8038045763969421},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6845970749855042},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6063252091407776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5774474143981934},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.5726996660232544},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5669986605644226},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5454387068748474},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5340240001678467},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4908373951911926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3175787925720215},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.31232595443725586},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1704103648662567},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11447912454605103}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.883728563785553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8038045763969421},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6845970749855042},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6063252091407776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5774474143981934},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.5726996660232544},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5669986605644226},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5454387068748474},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5340240001678467},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4908373951911926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3175787925720215},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.31232595443725586},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1704103648662567},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11447912454605103},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W109946471","https://openalex.org/W1555851617","https://openalex.org/W1576227399","https://openalex.org/W1579853615","https://openalex.org/W1836465849","https://openalex.org/W2000513720","https://openalex.org/W2029434926","https://openalex.org/W2064675550","https://openalex.org/W2471520273","https://openalex.org/W2598638573","https://openalex.org/W2745319348","https://openalex.org/W2767767449","https://openalex.org/W2778460379","https://openalex.org/W2801493797","https://openalex.org/W2889244839","https://openalex.org/W2921576841","https://openalex.org/W2962780374","https://openalex.org/W2972910332","https://openalex.org/W2990440871","https://openalex.org/W3007859642","https://openalex.org/W3015338123","https://openalex.org/W3015499232","https://openalex.org/W3097514409","https://openalex.org/W3133525064","https://openalex.org/W3158762648","https://openalex.org/W3160427568","https://openalex.org/W3187128306","https://openalex.org/W3190244907","https://openalex.org/W4280572880","https://openalex.org/W4280575909","https://openalex.org/W4286340542","https://openalex.org/W6603616073","https://openalex.org/W6631362777","https://openalex.org/W6634817459","https://openalex.org/W6637242042","https://openalex.org/W6712610176","https://openalex.org/W6713876852","https://openalex.org/W6766978945","https://openalex.org/W6779823529","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W1501596003","https://openalex.org/W2368036937"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3],"design":[4],"of":[5,72],"NNSVS,":[6],"an":[7,22],"open-source":[8,23],"soft-ware":[9],"for":[10],"neural":[11,44],"network-based":[12],"singing":[13,26,57],"voice":[14,27,58],"synthesis":[15,28,59],"research.":[16],"NNSVS":[17,47],"is":[18,80],"inspired":[19],"by":[20],"Sinsy,":[21],"pioneer":[24],"in":[25],"research,":[29],"and":[30,43,51,74],"provides":[31,48],"many":[32],"additional":[33],"features":[34],"such":[35],"as":[36],"multi-stream":[37],"models,":[38,42],"autoregressive":[39],"fundamental":[40],"frequency":[41],"vocoders.":[45],"Furthermore,":[46],"extensive":[49],"documentation":[50],"numerous":[52],"scripts":[53],"to":[54],"build":[55],"complete":[56],"systems.":[60,77],"Experimental":[61],"results":[62],"demonstrate":[63],"that":[64],"our":[65,70],"best":[66],"system":[67],"significantly":[68],"outperforms":[69],"reproduction":[71],"Sinsy":[73],"other":[75],"baseline":[76],"The":[78],"toolkit":[79],"available":[81],"at":[82],"https://github.com/nnsvs/nnsvs.":[83]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
