{"id":"https://openalex.org/W3095990227","doi":"https://doi.org/10.1109/taslp.2020.3034994","title":"NAUTILUS: A Versatile Voice Cloning System","display_name":"NAUTILUS: A Versatile Voice Cloning System","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3095990227","doi":"https://doi.org/10.1109/taslp.2020.3034994","mag":"3095990227"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3034994","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3034994","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09246264.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09246264.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002145453","display_name":"Hieu-Thi Luong","orcid":"https://orcid.org/0000-0002-4772-5995"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hieu-Thi Luong","raw_affiliation_strings":["National Institute of Informatics, and with the Department of Informatics, SOKENDAI (The Graduate University for Advanced Studies), Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4772-5995","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, and with the Department of Informatics, SOKENDAI (The Graduate University for Advanced Studies), Tokyo, Japan","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics and with the Department of Informatics, SOKENDAI (The Graduate University for Advanced Studies), Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2752-3955","affiliations":[{"raw_affiliation_string":"National Institute of Informatics and with the Department of Informatics, SOKENDAI (The Graduate University for Advanced Studies), Tokyo, Japan","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002145453"],"corresponding_institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"],"apc_list":null,"apc_paid":null,"fwci":5.1639,"has_fulltext":true,"cited_by_count":64,"citation_normalized_percentile":{"value":0.96290956,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"2967","last_page":"2981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.996999979019165,"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/T11309","display_name":"Music and Audio Processing","score":0.9930999875068665,"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/computer-science","display_name":"Computer science","score":0.7911465167999268},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7443599104881287},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5929499864578247},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.5768983960151672},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41508686542510986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7911465167999268},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7443599104881287},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5929499864578247},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.5768983960151672},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41508686542510986},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.3034994","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3034994","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09246264.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"}],"best_oa_location":{"id":"doi:10.1109/taslp.2020.3034994","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3034994","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09246264.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":[{"display_name":"Peace, Justice and strong institutions","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1526460031","display_name":null,"funder_award_id":"18H04112","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G1710514051","display_name":null,"funder_award_id":"17H04687","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G3582502417","display_name":null,"funder_award_id":"JPMJCR18A6","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G360976672","display_name":"Biometric Information Protection Utilization Infrastructure to Ensure Personal Convenience and Prevent Identity Theft","funder_award_id":"18H04120","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4104777191","display_name":null,"funder_award_id":"16H06302","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G5216536157","display_name":null,"funder_award_id":"18H04120","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G5375717198","display_name":null,"funder_award_id":"18KT0051","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"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/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6954941931","display_name":"Communication System for Defending against Attacks of Media Clones","funder_award_id":"16H06302","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7623259429","display_name":"Robust voice cloning technologies in noisy environments and its applications","funder_award_id":"17H04687","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7879866177","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G8315410620","display_name":null,"funder_award_id":"JPMJCR18A6","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G8937069383","display_name":"Safe and secure speech information processing based on liveness detection and ASVspoof challenge","funder_award_id":"18KT0051","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095990227.pdf","grobid_xml":"https://content.openalex.org/works/W3095990227.grobid-xml"},"referenced_works_count":110,"referenced_works":["https://openalex.org/W23142961","https://openalex.org/W33533989","https://openalex.org/W1492383498","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1576227399","https://openalex.org/W1588266896","https://openalex.org/W1597726554","https://openalex.org/W1630569004","https://openalex.org/W1959608418","https://openalex.org/W1984905644","https://openalex.org/W1991682319","https://openalex.org/W2035962301","https://openalex.org/W2115052578","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2142416747","https://openalex.org/W2149270762","https://openalex.org/W2154920538","https://openalex.org/W2293856338","https://openalex.org/W2408688265","https://openalex.org/W2413439388","https://openalex.org/W2494654097","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2532494225","https://openalex.org/W2553397501","https://openalex.org/W2559039559","https://openalex.org/W2584032004","https://openalex.org/W2595110011","https://openalex.org/W2605320104","https://openalex.org/W2746498480","https://openalex.org/W2759925408","https://openalex.org/W2767052532","https://openalex.org/W2786868129","https://openalex.org/W2788241093","https://openalex.org/W2788357188","https://openalex.org/W2802935216","https://openalex.org/W2806000759","https://openalex.org/W2808706139","https://openalex.org/W2810457573","https://openalex.org/W2887171382","https://openalex.org/W2887511658","https://openalex.org/W2889329491","https://openalex.org/W2892620417","https://openalex.org/W2899877258","https://openalex.org/W2903365642","https://openalex.org/W2903739847","https://openalex.org/W2921290812","https://openalex.org/W2938583109","https://openalex.org/W2938947737","https://openalex.org/W2939131199","https://openalex.org/W2949382160","https://openalex.org/W2950224550","https://openalex.org/W2952436057","https://openalex.org/W2962699523","https://openalex.org/W2962780374","https://openalex.org/W2963035245","https://openalex.org/W2963175743","https://openalex.org/W2963192573","https://openalex.org/W2963300588","https://openalex.org/W2963432880","https://openalex.org/W2963539064","https://openalex.org/W2963609956","https://openalex.org/W2963808252","https://openalex.org/W2963912679","https://openalex.org/W2963912924","https://openalex.org/W2963975282","https://openalex.org/W2964169091","https://openalex.org/W2964195110","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972473628","https://openalex.org/W2972569067","https://openalex.org/W2972999331","https://openalex.org/W2990440871","https://openalex.org/W2994715919","https://openalex.org/W2996414377","https://openalex.org/W3006777338","https://openalex.org/W3015707856","https://openalex.org/W3015826515","https://openalex.org/W3015853838","https://openalex.org/W3016106826","https://openalex.org/W3016160783","https://openalex.org/W3096567388","https://openalex.org/W3096650361","https://openalex.org/W3101689408","https://openalex.org/W6600922454","https://openalex.org/W6601370681","https://openalex.org/W6631362777","https://openalex.org/W6635216677","https://openalex.org/W6635861968","https://openalex.org/W6636567668","https://openalex.org/W6640963894","https://openalex.org/W6682344342","https://openalex.org/W6714016741","https://openalex.org/W6715633793","https://openalex.org/W6732429163","https://openalex.org/W6736204136","https://openalex.org/W6748588790","https://openalex.org/W6752888775","https://openalex.org/W6753855596","https://openalex.org/W6755135894","https://openalex.org/W6764115395","https://openalex.org/W6764398373","https://openalex.org/W6766442783","https://openalex.org/W6771070734","https://openalex.org/W6917585676","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2562096895","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W4307784074"],"abstract_inverted_index":{"We":[0,106],"introduce":[1],"a":[2,14,19,23,33],"novel":[3],"speech":[4,12,35,57],"synthesis":[5],"system,":[6],"called":[7],"NAUTILUS,":[8],"that":[9,129,153],"can":[10,51,81],"generate":[11],"with":[13,134,142,166],"target":[15,59,76],"voice":[16,98],"either":[17],"from":[18],"text":[20],"input":[21],"or":[22],"reference":[24],"utterance":[25],"of":[26,58,64,74,87,94,110,146],"an":[27],"arbitrary":[28],"source":[29],"speaker.":[30],"By":[31],"using":[32,55,115],"multi-speaker":[34],"corpus":[36],"to":[37,84,102,119,160],"train":[38],"all":[39],"requisite":[40],"encoders":[41],"and":[42,90,124,137,164],"decoders":[43,123],"in":[44],"the":[45,62,65,71,75,78,92,104,108,111,121,154,158],"initial":[46],"training":[47],"stage,":[48],"our":[49],"system":[50],"clone":[52],"unseen":[53],"voices":[54],"untranscribed":[56,147],"speakers":[60],"on":[61,70],"basis":[63],"backpropagation":[66],"algorithm.":[67],"Moreover,":[68,149],"depending":[69],"data":[72,89],"circumstance":[73],"speaker,":[77],"cloning":[79,141],"strategy":[80],"be":[82,172],"adjusted":[83],"take":[85],"advantage":[86],"additional":[88],"modify":[91],"behaviors":[93],"text-to-speech":[95],"(TTS)":[96],"and/or":[97],"conversion":[99],"(VC)":[100],"systems":[101,139],"accommodate":[103],"situation.":[105],"test":[107],"performance":[109],"proposed":[112,155],"framework":[113,156],"by":[114],"deep":[116],"convolution":[117],"layers":[118],"model":[120],"encoders,":[122],"WaveNet":[125],"vocoder.":[126],"Evaluations":[127],"show":[128],"it":[130,150],"achieves":[131],"comparable":[132],"quality":[133],"state-of-the-art":[135],"TTS":[136,163],"VC":[138,165],"when":[140],"just":[143],"five":[144],"minutes":[145],"speech.":[148],"is":[151],"demonstrated":[152],"has":[157],"ability":[159],"switch":[161],"between":[162],"high":[167],"speaker":[168],"consistency,":[169],"which":[170],"will":[171],"useful":[173],"for":[174],"many":[175],"applications.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}