{"id":"https://openalex.org/W3113687514","doi":"https://doi.org/10.1109/taslp.2020.3047262","title":"Many-to-Many Voice Transformer Network","display_name":"Many-to-Many Voice Transformer Network","publication_year":2020,"publication_date":"2020-12-24","ids":{"openalex":"https://openalex.org/W3113687514","doi":"https://doi.org/10.1109/taslp.2020.3047262","mag":"3113687514"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3047262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3047262","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3102-0162","affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"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":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3172-3335","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106710403","display_name":"Kou Tanaka","orcid":"https://orcid.org/0009-0003-7107-607X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kou Tanaka","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020693766","display_name":"Takuhiro Kaneko","orcid":"https://orcid.org/0009-0000-8016-5144"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuhiro Kaneko","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079710814","display_name":"Nobukatsu Hojo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobukatsu Hojo","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"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, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001243214"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":4.0768,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95022969,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"656","last_page":"670"},"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":0.9994000196456909,"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":0.9990000128746033,"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/transformer","display_name":"Transformer","score":0.7744684815406799},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7621933221817017},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6128578186035156},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5402599573135376},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.41067272424697876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37733787298202515},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0953814685344696},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09222444891929626},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07667988538742065},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07334849238395691}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7744684815406799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7621933221817017},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6128578186035156},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5402599573135376},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.41067272424697876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37733787298202515},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0953814685344696},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09222444891929626},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07667988538742065},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07334849238395691},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.3047262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3047262","pdf_url":null,"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":null,"license_id":null,"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":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":120,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W854541894","https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1902237438","https://openalex.org/W1965255698","https://openalex.org/W2005438552","https://openalex.org/W2017425464","https://openalex.org/W2017742648","https://openalex.org/W2022125261","https://openalex.org/W2056852181","https://openalex.org/W2057609679","https://openalex.org/W2076258817","https://openalex.org/W2093450784","https://openalex.org/W2105160541","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2130942839","https://openalex.org/W2142300631","https://openalex.org/W2148846882","https://openalex.org/W2156142001","https://openalex.org/W2157412983","https://openalex.org/W2284050935","https://openalex.org/W2395980997","https://openalex.org/W2404839462","https://openalex.org/W2471520273","https://openalex.org/W2517513811","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2584032004","https://openalex.org/W2591927543","https://openalex.org/W2608338293","https://openalex.org/W2613904329","https://openalex.org/W2619368999","https://openalex.org/W2733416080","https://openalex.org/W2748654097","https://openalex.org/W2749651610","https://openalex.org/W2767052532","https://openalex.org/W2769810959","https://openalex.org/W2785608393","https://openalex.org/W2796495654","https://openalex.org/W2800289214","https://openalex.org/W2804998325","https://openalex.org/W2811001736","https://openalex.org/W2890983311","https://openalex.org/W2897353073","https://openalex.org/W2899877258","https://openalex.org/W2901997113","https://openalex.org/W2902070858","https://openalex.org/W2911708970","https://openalex.org/W2941094131","https://openalex.org/W2945478979","https://openalex.org/W2946555236","https://openalex.org/W2947196194","https://openalex.org/W2949281321","https://openalex.org/W2962788625","https://openalex.org/W2962882868","https://openalex.org/W2962896155","https://openalex.org/W2963035245","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2963403868","https://openalex.org/W2963539064","https://openalex.org/W2963542740","https://openalex.org/W2963609956","https://openalex.org/W2963685250","https://openalex.org/W2963691546","https://openalex.org/W2963712897","https://openalex.org/W2963782041","https://openalex.org/W2963808252","https://openalex.org/W2963975282","https://openalex.org/W2964121744","https://openalex.org/W2964265128","https://openalex.org/W2964281804","https://openalex.org/W2964307104","https://openalex.org/W2970006822","https://openalex.org/W2970351109","https://openalex.org/W2972544500","https://openalex.org/W2972970915","https://openalex.org/W2972999331","https://openalex.org/W2990440871","https://openalex.org/W2997347790","https://openalex.org/W3015338123","https://openalex.org/W3024476726","https://openalex.org/W3034420534","https://openalex.org/W3034772996","https://openalex.org/W3096567388","https://openalex.org/W3098557217","https://openalex.org/W3099078140","https://openalex.org/W3100696337","https://openalex.org/W3113687514","https://openalex.org/W4288337064","https://openalex.org/W4289305009","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4385245566","https://openalex.org/W6603838645","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6679436768","https://openalex.org/W6695676441","https://openalex.org/W6712034360","https://openalex.org/W6726456654","https://openalex.org/W6732429163","https://openalex.org/W6736811364","https://openalex.org/W6736996214","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6743301281","https://openalex.org/W6743855016","https://openalex.org/W6748381320","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6753855596","https://openalex.org/W6756159577","https://openalex.org/W6756197946","https://openalex.org/W6762533536","https://openalex.org/W6767111847","https://openalex.org/W6772381481","https://openalex.org/W6777080322"],"related_works":["https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W3048844891","https://openalex.org/W1992327129","https://openalex.org/W2381986121","https://openalex.org/W2370918718","https://openalex.org/W2256933480","https://openalex.org/W2370081953","https://openalex.org/W2027854990","https://openalex.org/W2387659881"],"abstract_inverted_index":{"This":[0,88],"paper":[1],"proposes":[2],"a":[3,10,38,56,124,204],"voice":[4,21,44],"conversion":[5,18,180,213],"(VC)":[6],"method":[7,36],"based":[8],"on":[9],"sequence-to-sequence":[11],"(S2S)":[12],"learning":[13],"framework,":[14],"which":[15],"enables":[16,94],"simultaneous":[17],"of":[19,27,58,76,170],"the":[20,43,68,77,91,128,135,143,150,168,171],"characteristics,":[22],"pitch":[23],"contour,":[24],"and":[25,145,182,191],"duration":[26],"input":[28,136],"speech.":[29],"We":[30,176,197],"previously":[31],"proposed":[32],"an":[33,74],"S2S-based":[34],"VC":[35],"using":[37],"transformer":[39,45],"network":[40,46],"architecture":[41],"called":[42,90,127],"(VTN).":[47],"The":[48],"original":[49,78],"VTN":[50,79],"was":[51],"designed":[52],"to":[53,65,96,122,132,162,207],"learn":[54,83],"only":[55],"mapping":[57,130],"speech":[59],"feature":[60,137],"sequences":[61],"from":[62,103],"one":[63],"speaker":[64,147,178,192],"another.":[66],"Here,":[67],"main":[69],"idea":[70],"we":[71],"propose":[72],"is":[73],"extension":[75],"that":[80,111,134,184,200],"can":[81,112,210],"simultaneously":[82],"mappings":[84],"among":[85],"multiple":[86,104],"speakers.":[87,117],"extension,":[89],"many-to-many":[92],"VTN,":[93],"us":[95,121],"fully":[97],"use":[98],"available":[99],"training":[100,125,158],"data":[101],"collected":[102],"speakers":[105],"by":[106],"capturing":[107],"common":[108],"latent":[109],"features":[110],"be":[113,163],"shared":[114],"across":[115],"different":[116],"It":[118],"also":[119,198],"allows":[120],"introduce":[123],"loss":[126,131,155],"identity":[129,179],"ensure":[133],"sequence":[138],"will":[139],"remain":[140],"unchanged":[141],"when":[142],"source":[144],"target":[146],"indices":[148],"are":[149],"same.":[151],"Using":[152],"this":[153],"particular":[154],"for":[156],"model":[157,172,186],"has":[159],"been":[160],"found":[161,183,199],"extremely":[164],"effective":[165],"in":[166],"improving":[167],"performance":[169],"at":[173],"test":[174],"time.":[175],"conducted":[177],"experiments":[181],"our":[185,201],"obtained":[187],"higher":[188],"sound":[189],"quality":[190],"similarity":[193],"than":[194],"baseline":[195],"methods.":[196],"model,":[202],"with":[203],"slight":[205],"modification":[206],"its":[208],"architecture,":[209],"handle":[211],"any-to-many":[212],"tasks":[214],"reasonably":[215],"well.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}