{"id":"https://openalex.org/W4403510345","doi":"https://doi.org/10.1109/lsp.2024.3482701","title":"Multi-Speaker Text-to-Speech Training With Speaker Anonymized Data","display_name":"Multi-Speaker Text-to-Speech Training With Speaker Anonymized Data","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403510345","doi":"https://doi.org/10.1109/lsp.2024.3482701"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3482701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3482701","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/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":["Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan","Graduate School of Informatics, Nagoya University, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3172-3335","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":["Meta, Menlo Park, CA, USA","Meta, USA"],"raw_orcid":"https://orcid.org/0000-0003-4390-1354","affiliations":[{"raw_affiliation_string":"Meta, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Meta, USA","institution_ids":[]}]},{"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":["Information Technology Center, Nagoya University, Nagoya, Aichi, Japan","Information Technology Center, Nagoya University, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8146-1279","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1114,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81671684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"2995","last_page":"2999"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9836000204086304,"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":0.9836000204086304,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9650999903678894,"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/speech-recognition","display_name":"Speech recognition","score":0.7782427072525024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7516988515853882},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6939418315887451},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6765512228012085},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5255084037780762},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4611774682998657},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4357127547264099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3180537521839142}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7782427072525024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516988515853882},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6939418315887451},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6765512228012085},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5255084037780762},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4611774682998657},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4357127547264099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3180537521839142},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3482701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3482701","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2471520273","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2963609956","https://openalex.org/W2972359262","https://openalex.org/W2972848589","https://openalex.org/W2981087920","https://openalex.org/W3197008493","https://openalex.org/W3209059054","https://openalex.org/W4210970267","https://openalex.org/W4225956675","https://openalex.org/W4306867200","https://openalex.org/W4372260248","https://openalex.org/W4381786045","https://openalex.org/W4389961181","https://openalex.org/W4400770760","https://openalex.org/W6750489868","https://openalex.org/W6763832098","https://openalex.org/W6796464841","https://openalex.org/W6802659129","https://openalex.org/W6805710207","https://openalex.org/W6810332117","https://openalex.org/W6810404315","https://openalex.org/W6848735303","https://openalex.org/W6859583170","https://openalex.org/W6861342446","https://openalex.org/W6862144568","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W4247736853","https://openalex.org/W1521049138","https://openalex.org/W2997340161","https://openalex.org/W1589374915","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"The":[0],"trend":[1],"of":[2,11,15,18,37,58,123,151,157,168,175],"scaling":[3],"up":[4],"speech":[5,61],"generation":[6],"models":[7,41],"poses":[8],"the":[9,16,19,22,35,55,59,102,114,121,124,149,158,166,173,176],"threat":[10],"biometric":[12],"information":[13],"leakage":[14],"identities":[17],"voices":[20],"in":[21,165],"training":[23,36,116],"data,":[24,117],"raising":[25],"privacy":[26],"and":[27,69,109,143],"security":[28],"concerns.":[29],"In":[30],"this":[31],"letter,":[32],"we":[33,133],"investigate":[34],"multi-speaker":[38,82,180],"text-to-speech":[39],"(TTS)":[40],"using":[42,129],"data":[43],"that":[44,51,135,147],"underwent":[45],"speaker":[46,56,99],"anonymization":[47],"(SA),":[48],"a":[49,81,137,145],"process":[50],"tends":[52],"to":[53,78,89,96,112],"hide":[54],"identity":[57],"input":[60],"while":[62],"maintaining":[63],"other":[64],"attributes.":[65],"Two":[66],"signal":[67],"processing-based":[68],"three":[70],"deep":[71],"neural":[72],"network-based":[73],"SA":[74,177],"methods":[75],"were":[76],"used":[77,88],"anonymize":[79],"VCTK,":[80],"TTS":[83,93,100,126,160,181],"dataset,":[84],"which":[85],"is":[86],"further":[87],"train":[90],"an":[91],"end-to-end":[92],"model,":[94,142],"VITS,":[95],"perform":[97],"unseen":[98],"during":[101],"testing":[103],"phase.":[104],"We":[105,162],"conducted":[106],"extensive":[107],"objective":[108],"subjective":[110,139],"experiments":[111],"evaluate":[113],"anonymized":[115],"as":[118,120],"well":[119],"performance":[122],"downstream":[125,159],"model":[127],"trained":[128],"those":[130],"data.":[131],"Importantly,":[132],"found":[134],"UTMOS,":[136],"data-driven":[138],"rating":[140],"predictor":[141],"GVD,":[144],"metric":[146],"measures":[148],"gain":[150],"voice":[152],"distinctiveness,":[153],"are":[154],"good":[155],"indicators":[156],"performance.":[161],"summarize":[163],"insights":[164],"hope":[167],"helping":[169],"future":[170],"researchers":[171],"determine":[172],"usefulness":[174],"system":[178],"for":[179],"training.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}