{"id":"https://openalex.org/W4312822384","doi":"https://doi.org/10.1109/access.2022.3227963","title":"Zero-Shot Unseen Speaker Anonymization via Voice Conversion","display_name":"Zero-Shot Unseen Speaker Anonymization via Voice Conversion","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312822384","doi":"https://doi.org/10.1109/access.2022.3227963"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3227963","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3227963","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2022.3227963","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033795998","display_name":"Hyung-Pil Chang","orcid":"https://orcid.org/0000-0003-0265-3382"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyung-Pil Chang","raw_affiliation_strings":["Department of Computer Science and Engineering, Artificial Intelligence Laboratory, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-0265-3382","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Artificial Intelligence Laboratory, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068783691","display_name":"In-Chul Yoo","orcid":"https://orcid.org/0000-0001-7129-047X"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"In-Chul Yoo","raw_affiliation_strings":["Department of Computer Science and Engineering, Artificial Intelligence Laboratory, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-7129-047X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Artificial Intelligence Laboratory, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083454120","display_name":"Changhyeon Jeong","orcid":"https://orcid.org/0000-0001-7590-3835"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changhyeon Jeong","raw_affiliation_strings":["Department of Computer Science and Engineering, Artificial Intelligence Laboratory, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-7590-3835","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Artificial Intelligence Laboratory, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039833822","display_name":"Dongsuk Yook","orcid":"https://orcid.org/0000-0003-2445-2354"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongsuk Yook","raw_affiliation_strings":["Department of Computer Science and Engineering, Artificial Intelligence Laboratory, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-2445-2354","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Artificial Intelligence Laboratory, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033795998"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.5555,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73158296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"10","issue":null,"first_page":"130190","last_page":"130199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9979000091552734,"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":0.9872999787330627,"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":0.8613435626029968},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7368628978729248},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6473590135574341},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.597111701965332},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5187056660652161},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5076030492782593},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4531632959842682},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4440300464630127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34082749485969543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8613435626029968},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7368628978729248},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6473590135574341},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.597111701965332},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5187056660652161},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5076030492782593},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4531632959842682},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4440300464630127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34082749485969543},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":2,"locations":[{"id":"doi:10.1109/access.2022.3227963","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3227963","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3377a4a66af94d80b8c0765a2dfdd743","is_oa":true,"landing_page_url":"https://doaj.org/article/3377a4a66af94d80b8c0765a2dfdd743","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 130190-130199 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3227963","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3227963","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2182629084","display_name":null,"funder_award_id":"NRF-2017R1E1A1A01078157","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1959608418","https://openalex.org/W2041823554","https://openalex.org/W2046875449","https://openalex.org/W2107860279","https://openalex.org/W2140190241","https://openalex.org/W2144760012","https://openalex.org/W2150769028","https://openalex.org/W2165880886","https://openalex.org/W2194775991","https://openalex.org/W2281963941","https://openalex.org/W2331222812","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2567070169","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2887902433","https://openalex.org/W2890964092","https://openalex.org/W2902070858","https://openalex.org/W2910453440","https://openalex.org/W2945478979","https://openalex.org/W2946555236","https://openalex.org/W2951082691","https://openalex.org/W2962780374","https://openalex.org/W2963035245","https://openalex.org/W2963300588","https://openalex.org/W2963499153","https://openalex.org/W2970006822","https://openalex.org/W2972659941","https://openalex.org/W2997400081","https://openalex.org/W3015959238","https://openalex.org/W3024443431","https://openalex.org/W3024768724","https://openalex.org/W3092028330","https://openalex.org/W3095232705","https://openalex.org/W3096025930","https://openalex.org/W3096424617","https://openalex.org/W3096697361","https://openalex.org/W3097952294","https://openalex.org/W3163793923","https://openalex.org/W4200256530","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6731370813","https://openalex.org/W6762533536","https://openalex.org/W6767111847","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2148232863","https://openalex.org/W2160753975","https://openalex.org/W2161543916","https://openalex.org/W2111874347","https://openalex.org/W2640905660"],"abstract_inverted_index":{"Speech-based":[0],"interfaces":[1,12],"provide":[2],"convenient":[3],"methods":[4,185],"for":[5,186,245],"controlling":[6],"various":[7,20],"smart":[8],"devices.":[9],"For":[10],"these":[11],"to":[13,28,89,116,127,145],"work":[14],"reliably,":[15],"considerable":[16],"speech":[17,240,267],"data":[18,77],"with":[19,51,219],"noise":[21],"and":[22,206,233,239,264],"speaker":[23,104,121,189,196,255,278],"characteristics":[24,166],"must":[25],"be":[26,87,150,216],"collected":[27],"train":[29],"the":[30,52,62,70,75,96,110,117,134,164,174,178,187,192,210,231,253,265,277,281],"associated":[31],"speech-processing":[32],"models.":[33],"Gathering":[34],"spoken":[35,66,76],"commands":[36,67],"from":[37,133],"actual":[38],"users":[39],"of":[40,56,65,72,99,112,139,177],"devices":[41],"can":[42,86,161,215],"improve":[43],"those":[44],"devices\u2019":[45],"performance":[46],"by":[47,260,272,280],"familiarizing":[48],"each":[49],"device":[50],"individual":[53,165],"acoustic":[54],"characteristic":[55],"its":[57],"particular":[58],"user\u2019s":[59,101],"speech.":[60,102,179],"However,":[61],"direct":[63],"acquisition":[64],"could":[68,107],"threaten":[69],"privacy":[71],"users,":[73],"as":[74,146],"would":[78],"contain":[79],"sensitive":[80,92],"speaker-specific":[81],"information.":[82],"Speaker":[83,236],"anonymization":[84,105,122,279],"algorithms":[85,106,123,205],"applied":[88,126],"suppress":[90,163],"such":[91,141],"information,":[93],"while":[94,172],"preserving":[95],"linguistic":[97,175],"content":[98,176],"a":[100,137,157],"Previous":[103],"handle":[108],"only":[109],"voice":[111,183,203,222],"speakers":[113,129,142],"who":[114],"contributed":[115],"training":[118,135],"datasets.":[119],"As":[120],"are":[124,131,243],"typically":[125],"new":[128],"(who":[130],"absent":[132],"datasets),":[136],"method":[138,159,194,227],"handling":[140],"(commonly":[143],"referred":[144],"\u201cunseen":[147],"speakers\u201d)":[148],"should":[149],"developed.":[151],"In":[152],"this":[153],"paper,":[154],"we":[155],"propose":[156],"novel":[158],"that":[160,252],"effectively":[162],"in":[167,201],"an":[168],"unseen":[169,188],"speaker\u2019s":[170],"voice,":[171],"retaining":[173],"It":[180],"adopts":[181],"zero-shot":[182],"conversion":[184,204,211,223],"anonymization.":[190],"Since":[191],"proposed":[193,226,282],"utilizes":[195],"identity":[197],"vectors":[198],"commonly":[199],"used":[200,244],"many-to-many":[202],"does":[207],"not":[208],"modify":[209],"algorithm":[212],"itself,":[213],"it":[214],"easily":[217],"combined":[218],"many":[220],"other":[221],"algorithms.":[224],"The":[225,248],"is":[228],"evaluated":[229],"using":[230],"VCC2018":[232],"VCTK":[234],"corpora.":[235],"identification":[237,256],"rate":[238,242],"recognition":[241,268],"quantitative":[246],"analysis.":[247],"experimental":[249],"results":[250],"showed":[251],"average":[254,266],"accuracy":[257,269],"was":[258,270],"decreased":[259,271],"92.3%":[261],"point":[262,274],"absolutely":[263,275],"17.7%":[273],"after":[276],"method.":[283]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}