{"id":"https://openalex.org/W7148285181","doi":"https://doi.org/10.1109/asru65441.2025.11434785","title":"SEF-MK: Speaker-Embedding-Free Voice Anonymization through Multi-k-means Quantization","display_name":"SEF-MK: Speaker-Embedding-Free Voice Anonymization through Multi-k-means Quantization","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148285181","doi":"https://doi.org/10.1109/asru65441.2025.11434785"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-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/A5132821426","display_name":"Beilong Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Beilong Tang","raw_affiliation_strings":["Duke Kunshan University,China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132810944","display_name":"Xiaoxiao Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxiao Miao","raw_affiliation_strings":["Duke Kunshan University,China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132801370","display_name":"Ming Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Duke Kunshan University,China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5132821426"],"corresponding_institution_ids":["https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":2.1819,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9293588,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6517000198364258,"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":0.6517000198364258,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0364999994635582,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.032600000500679016,"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/utterance","display_name":"Utterance","score":0.7982000112533569},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.7289000153541565},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.7250000238418579},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5436000227928162},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5242000222206116},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44290000200271606}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7982000112533569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506999969482422},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.7289000153541565},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7250000238418579},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5436000227928162},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5386000275611877},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45019999146461487},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3921000063419342},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2972359262","https://openalex.org/W2972848589","https://openalex.org/W3005862564","https://openalex.org/W3024768724","https://openalex.org/W3024869864","https://openalex.org/W3043999252","https://openalex.org/W3097777922","https://openalex.org/W3180600971","https://openalex.org/W3197008493","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3216758611","https://openalex.org/W4210970267","https://openalex.org/W4221114270","https://openalex.org/W4221152846","https://openalex.org/W4297841874","https://openalex.org/W4319862433","https://openalex.org/W4372260248","https://openalex.org/W4385823432","https://openalex.org/W4386557792","https://openalex.org/W4386712580","https://openalex.org/W4392902635","https://openalex.org/W4399485371","https://openalex.org/W4400770760","https://openalex.org/W4402112376","https://openalex.org/W4402112474","https://openalex.org/W4403310030","https://openalex.org/W4403311272","https://openalex.org/W4406461461","https://openalex.org/W4409019657","https://openalex.org/W4409058573","https://openalex.org/W4410065299","https://openalex.org/W4415433544"],"related_works":[],"abstract_inverted_index":{"Voice":[0],"anonymization":[1,127],"protects":[2],"speaker":[3,23],"privacy":[4,117],"by":[5,52],"concealing":[6],"identity":[7],"while":[8],"preserving":[9],"linguistic":[10,19,96],"and":[11,75,97,137],"paralinguistic":[12],"content.":[13],"Self-supervised":[14],"learning":[15],"(SSL)":[16],"representations":[17,48],"encode":[18],"features":[20],"but":[21],"preserve":[22],"traits.":[24],"We":[25,68],"propose":[26],"a":[27,36,63,84],"novel":[28],"speaker-embedding-free":[29],"framework":[30],"called":[31],"SEF-MK.":[32],"Instead":[33],"of":[34,56,66,116],"using":[35],"single":[37,85],"k-means":[38,58],"model":[39],"trained":[40,61],"on":[41,62],"the":[42,101,106,114],"entire":[43],"dataset,":[44],"SEF-MK":[45,89],"anonymizes":[46],"SSL":[47],"for":[49],"each":[50,60],"utterance":[51],"randomly":[53],"selecting":[54],"one":[55],"multiple":[57,91,110],"models,":[59],"different":[64],"subset":[65],"speakers.":[67],"explore":[69],"this":[70],"approach":[71],"from":[72,100,105],"both":[73],"attacker":[74,131],"user":[76],"perspectives.":[77],"Extensive":[78],"experiments":[79],"show":[80],"that,":[81],"compared":[82],"to":[83,129],"k":[86],"-means":[87],"model,":[88],"with":[90],"$\\mathbf{k}$-means":[92,111],"models":[93,112],"better":[94],"preserves":[95],"emotional":[98],"content":[99],"user\u2019s":[102],"viewpoint.":[103],"However,":[104],"attacker\u2019s":[107],"perspective,":[108],"utilizing":[109],"boosts":[113],"effectiveness":[115],"attacks.":[118],"These":[119],"insights":[120],"can":[121,140],"aid":[122],"users":[123],"in":[124],"designing":[125],"voice":[126],"systems":[128],"mitigate":[130],"threats.<sup":[132],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[133,135],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[134],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Code":[136],"audio":[138],"samples":[139],"be":[141],"found":[142],"at":[143],"https://github.com/Beilong-Tang/sef-mk":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}