{"id":"https://openalex.org/W4297841415","doi":"https://doi.org/10.21437/interspeech.2022-11036","title":"DeID-VC: Speaker De-identification via Zero-shot Pseudo Voice Conversion","display_name":"DeID-VC: Speaker De-identification via Zero-shot Pseudo Voice Conversion","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841415","doi":"https://doi.org/10.21437/interspeech.2022-11036"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11036","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11036","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/A5067150934","display_name":"Ruibin Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruibin Yuan","raw_affiliation_strings":["Carnegie Mellon University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020339836","display_name":"Yuxuan Wu","orcid":"https://orcid.org/0000-0003-1333-4627"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxuan Wu","raw_affiliation_strings":["Carnegie Mellon University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028332454","display_name":"Jacob Li","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Li","raw_affiliation_strings":["Carnegie Mellon University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083475504","display_name":"Jaxter Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaxter Kim","raw_affiliation_strings":["Carnegie Mellon University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2593","last_page":"2597"},"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":0.9998000264167786,"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":0.9980999827384949,"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/speaker-identification","display_name":"Speaker identification","score":0.7397923469543457},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6800175905227661},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6186407208442688},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5353973507881165},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.517264187335968},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.44764965772628784},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05621042847633362}],"concepts":[{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.7397923469543457},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6800175905227661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6186407208442688},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5353973507881165},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.517264187335968},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.44764965772628784},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05621042847633362},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11036","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11036","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1973207880","https://openalex.org/W2046056978","https://openalex.org/W2128466129","https://openalex.org/W2407075323","https://openalex.org/W2519091744","https://openalex.org/W2562637781","https://openalex.org/W2772024149","https://openalex.org/W2806521799","https://openalex.org/W2945478979","https://openalex.org/W2962780374","https://openalex.org/W2962788625","https://openalex.org/W2972848589","https://openalex.org/W2972956697","https://openalex.org/W2981087920","https://openalex.org/W2994294114","https://openalex.org/W3005862564","https://openalex.org/W3012170331","https://openalex.org/W3024768724","https://openalex.org/W3024869864","https://openalex.org/W3034635067","https://openalex.org/W3092028330","https://openalex.org/W3167533889","https://openalex.org/W4210970267","https://openalex.org/W4287632938","https://openalex.org/W4309451541","https://openalex.org/W4391602018"],"related_works":["https://openalex.org/W2410566519","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W4234190324","https://openalex.org/W321304764","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W2249138175","https://openalex.org/W2154141294"],"abstract_inverted_index":{"The":[0],"widespread":[1],"adoption":[2],"of":[3,70,93,123,151],"speech-based":[4],"online":[5],"services":[6],"raises":[7],"security":[8],"and":[9,18,82,121,136,164],"privacy":[10],"concerns":[11],"regarding":[12],"the":[13,20,61,91,117,148],"data":[14,21],"that":[15,49,155],"they":[16],"use":[17],"share.If":[19],"were":[22],"compromised,":[23],"attackers":[24],"could":[25],"exploit":[26],"user":[27],"speech":[28],"to":[29,54,115,146,171],"bypass":[30],"speaker":[31,46,53,102],"verification":[32],"systems":[33],"or":[34,59,104],"even":[35,105],"impersonate":[36],"users.To":[37],"mitigate":[38],"this,":[39],"we":[40],"propose":[41],"DeID-VC":[42,71,95],"1":[43],",":[44],"a":[45,51,65,73,83],"de-identification":[47,165],"system":[48],"converts":[50],"real":[52],"pseudo":[55,99],"speakers,":[56],"thus":[57],"removing":[58],"obfuscating":[60],"speakerdependent":[62],"attributes":[63],"from":[64],"spoken":[66],"voice.The":[67],"key":[68],"components":[69],"include":[72],"Variational":[74],"Autoencoder":[75,86],"(VAE)":[76],"based":[77],"Pseudo":[78],"Speaker":[79],"Generator":[80],"(PSG)":[81],"voice":[84,125],"conversion":[85],"(AE)":[87],"under":[88],"zero-shot":[89,124],"settings.With":[90],"help":[92],"PSG,":[94],"can":[96],"assign":[97],"unique":[98],"speakers":[100],"at":[101,106],"level":[103],"utterance":[107],"level.Also,":[108],"two":[109],"novel":[110],"learning":[111],"objectives":[112],"are":[113],"added":[114],"bridge":[116],"gap":[118],"between":[119],"training":[120],"inference":[122],"conversion.We":[126],"present":[127],"our":[128,156,172],"experimental":[129],"results":[130],"with":[131,142],"word":[132],"error":[133,138],"rate":[134,139],"(WER)":[135],"equal":[137],"(EER),":[140],"along":[141],"three":[143],"subjective":[144],"metrics":[145],"evaluate":[147],"generated":[149],"output":[150],"DeID-VC.The":[152],"result":[153],"shows":[154],"method":[157],"substantially":[158],"improved":[159],"intelligibility":[160],"(WER":[161],"10%":[162],"lower)":[163],"effectiveness":[166],"(EER":[167],"5%":[168],"higher)":[169],"compared":[170],"baseline.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}