{"id":"https://openalex.org/W3015437531","doi":"https://doi.org/10.1109/icassp40776.2020.9053811","title":"Fast and High-Quality Singing Voice Synthesis System Based on Convolutional Neural Networks","display_name":"Fast and High-Quality Singing Voice Synthesis System Based on Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015437531","doi":"https://doi.org/10.1109/icassp40776.2020.9053811","mag":"3015437531"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5016084389","display_name":"Kazuhiro Nakamura","orcid":"https://orcid.org/0000-0002-6095-8996"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kazuhiro Nakamura","raw_affiliation_strings":["Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":["Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067594810","display_name":"Kei Hashimoto","orcid":"https://orcid.org/0000-0003-2081-0396"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kei Hashimoto","raw_affiliation_strings":["Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049909008","display_name":"Keiichiro Oura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keiichiro Oura","raw_affiliation_strings":["Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan","institution_ids":[]}]},{"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, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, 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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Research and Development, Techno-Speech, Inc., Nagoya, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5016084389"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4245,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.89289006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7239","last_page":"7243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9950000047683716,"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":0.9382421970367432},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8940179347991943},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.773139476776123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7282418012619019},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6587689518928528},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5501327514648438},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45274999737739563},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4419378340244293},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4265501797199249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41591233015060425},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.41218191385269165},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.357820600271225},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13101395964622498}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9382421970367432},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8940179347991943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773139476776123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7282418012619019},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6587689518928528},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5501327514648438},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45274999737739563},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4419378340244293},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4265501797199249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41591233015060425},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.41218191385269165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.357820600271225},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13101395964622498},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":43,"referenced_works":["https://openalex.org/W1502723613","https://openalex.org/W1576227399","https://openalex.org/W1903029394","https://openalex.org/W2049686551","https://openalex.org/W2064675550","https://openalex.org/W2102003408","https://openalex.org/W2119196219","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2154920538","https://openalex.org/W2160815625","https://openalex.org/W2294797155","https://openalex.org/W2394662942","https://openalex.org/W2402539796","https://openalex.org/W2403471241","https://openalex.org/W2515336442","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2606052883","https://openalex.org/W2666279857","https://openalex.org/W2749651610","https://openalex.org/W2790645443","https://openalex.org/W2890983311","https://openalex.org/W2892140764","https://openalex.org/W2921576841","https://openalex.org/W2962883485","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2972910332","https://openalex.org/W2973046048","https://openalex.org/W4298580827","https://openalex.org/W6675380101","https://openalex.org/W6677750764","https://openalex.org/W6696843773","https://openalex.org/W6712239235","https://openalex.org/W6732429163","https://openalex.org/W6736068285","https://openalex.org/W6739959895","https://openalex.org/W6743855016","https://openalex.org/W6748409065","https://openalex.org/W6754925833","https://openalex.org/W6755592152"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W172797710","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W2909357361","https://openalex.org/W4387098302","https://openalex.org/W4288365855","https://openalex.org/W2948317131","https://openalex.org/W2111961547"],"abstract_inverted_index":{"The":[0],"present":[1],"paper":[2],"describes":[3],"singing":[4,34,37,61,126],"voice":[5,14],"synthesis":[6,15],"based":[7,17],"on":[8,18,107],"convolutional":[9],"neural":[10,20],"networks":[11,21],"(CNNs).":[12],"Singing":[13],"systems":[16],"deep":[19],"(DNNs)":[22],"are":[23,28,63],"currently":[24],"being":[25],"proposed":[26,56,120],"and":[27,81],"improving":[29],"the":[30,55,88,100,119,131],"naturalness":[31],"of":[32,43,60,78,109],"synthesized":[33],"voices.":[35],"As":[36],"voices":[38,62,127],"represent":[39],"a":[40,45,82,93],"rich":[41],"form":[42],"expression,":[44],"powerful":[46],"technique":[47],"to":[48],"model":[49],"them":[50],"accurately":[51],"is":[52,71,85,113],"required.":[53],"In":[54],"technique,":[57,97],"long-term":[58,79],"dependencies":[59],"modeled":[64],"by":[65],"CNNs.":[66],"An":[67],"acoustic":[68],"feature":[69],"sequence":[70],"generated":[72],"for":[73],"each":[74],"segment":[75],"that":[76,118],"consists":[77],"frames,":[80],"natural":[83,124],"trajectory":[84],"obtained":[86],"without":[87],"parameter":[89],"generation":[90],"algorithm.":[91],"Furthermore,":[92],"computational":[94],"complexity":[95],"reduction":[96],"which":[98],"drives":[99],"DNNs":[101],"in":[102],"different":[103],"time":[104],"units":[105],"depending":[106],"type":[108],"musical":[110],"score":[111],"features,":[112],"proposed.":[114],"Experimental":[115],"results":[116],"show":[117],"method":[121],"can":[122],"synthesize":[123],"sounding":[125],"much":[128],"faster":[129],"than":[130],"conventional":[132],"method.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}