{"id":"https://openalex.org/W7155100713","doi":"https://doi.org/10.48550/arxiv.2604.17000","title":"Anonymization, Not Elimination: Utility-Preserved Speech Anonymization","display_name":"Anonymization, Not Elimination: Utility-Preserved Speech Anonymization","publication_year":2026,"publication_date":"2026-04-18","ids":{"openalex":"https://openalex.org/W7155100713","doi":"https://doi.org/10.48550/arxiv.2604.17000"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2604.17000","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.17000","pdf_url":"https://arxiv.org/pdf/2604.17000","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2604.17000","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134162671","display_name":"Yunchong Xiao","orcid":"https://orcid.org/0009-0006-1778-152X","observed_orcids":["https://orcid.org/0009-0006-1778-152X"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao, Yunchong","raw_affiliation_strings":["LANCE Lab , School of Computer Science , MoE Key Lab of Artificial Intelligence , Shanghai Jiao Tong University , Shanghai 200240 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LANCE Lab , School of Computer Science , MoE Key Lab of Artificial Intelligence , Shanghai Jiao Tong University , Shanghai 200240 , China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129683563","display_name":"Yuxiang Zhao","orcid":"https://orcid.org/0009-0007-2877-2271","observed_orcids":["https://orcid.org/0009-0007-2877-2271"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yuxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134101008","display_name":"Ziyang Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Ziyang","raw_affiliation_strings":["LANCE Lab , School of Computer Science , MoE Key Lab of Artificial Intelligence , Shanghai Jiao Tong University , Shanghai 200240 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LANCE Lab , School of Computer Science , MoE Key Lab of Artificial Intelligence , Shanghai Jiao Tong University , Shanghai 200240 , China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134168915","display_name":"Shuai Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Shuai","raw_affiliation_strings":["LANCE Lab , School of Computer Science , MoE Key Lab of Artificial Intelligence , Shanghai Jiao Tong University , Shanghai 200240 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LANCE Lab , School of Computer Science , MoE Key Lab of Artificial Intelligence , Shanghai Jiao Tong University , Shanghai 200240 , China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137626887","display_name":"Kai Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Kai","raw_affiliation_strings":["LANCE Lab , School of Computer Science , MoE Key Lab of Artificial Intelligence , Shanghai Jiao Tong University , Shanghai 200240 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LANCE Lab , School of Computer Science , MoE Key Lab of Artificial Intelligence , Shanghai Jiao Tong University , Shanghai 200240 , China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048397143","display_name":"Jiachun Liao","orcid":"https://orcid.org/0000-0001-7439-4645","observed_orcids":["https://orcid.org/0000-0001-7439-4645"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liao, Jiachun","raw_affiliation_strings":["LANCE Lab , School of Computer Science , MoE Key Lab of Artificial Intelligence , Shanghai Jiao Tong University , Shanghai 200240 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LANCE Lab , School of Computer Science , MoE Key Lab of Artificial Intelligence , Shanghai Jiao Tong University , Shanghai 200240 , China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134189127","display_name":"Xie Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Xie","raw_affiliation_strings":["LANCE Lab , School of Computer Science , MoE Key Lab of Artificial Intelligence , Shanghai Jiao Tong University , Shanghai 200240 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LANCE Lab , School of Computer Science , MoE Key Lab of Artificial Intelligence , Shanghai Jiao Tong University , Shanghai 200240 , China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9229000210762024,"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":0.9229000210762024,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.04529999941587448,"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":0.013000000268220901,"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/utility-preservation","display_name":"utility preservation","score":0.5730000138282776},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.8989999890327454},{"id":"https://openalex.org/keywords/voice-privacy","display_name":"voice privacy","score":0.6610000133514404},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"speaker verification","score":0.7200000286102295},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8059999942779541},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.9819999933242798},{"id":"https://openalex.org/keywords/speech-emotion-recognition","display_name":"speech emotion recognition","score":0.996999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209999799728394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5623000264167786},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43529999256134033},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.42969998717308044},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.38830000162124634},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33489999175071716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31790000200271606},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C3017597292","wikidata":"https://www.wikidata.org/wiki/Q25052250","display_name":"Privacy protection","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2604.17000","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.17000","pdf_url":"https://arxiv.org/pdf/2604.17000","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2604.17000","doi":"https://doi.org/10.48550/arxiv.2604.17000","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17000","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2604.17000","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.17000","pdf_url":"https://arxiv.org/pdf/2604.17000","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","score":0.7333195805549622,"id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G3278014984","display_name":null,"funder_award_id":"U23B2018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7155100713.pdf","grobid_xml":"https://content.openalex.org/works/W7155100713.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4372260098","https://openalex.org/W4385822306","https://openalex.org/W4319862433","https://openalex.org/W4385749691","https://openalex.org/W4281250109","https://openalex.org/W7204215982","https://openalex.org/W4385822764","https://openalex.org/W4386712546","https://openalex.org/W4206231964","https://openalex.org/W4284706634"],"abstract_inverted_index":{"The":[0],"growing":[1],"reliance":[2],"on":[3,65],"large-scale":[4],"speech":[5,37,70,109,206],"data":[6,20,38],"has":[7],"made":[8],"privacy":[9,149,178,208],"protection":[10,179],"a":[11,76,87,107,126,131,143,197],"critical":[12],"concern.":[13],"However,":[14],"existing":[15],"anonymization":[16,128],"approaches":[17],"often":[18],"degrade":[19],"utility,":[21],"for":[22,39,120],"example":[23],"by":[24,161],"disrupting":[25],"acoustic":[26,97],"continuity":[27],"or":[28],"reducing":[29],"vocal":[30],"diversity,":[31],"which":[32],"compromises":[33],"the":[34,188,192,202],"value":[35],"of":[36,68,79,201,204],"downstream":[40],"tasks":[41],"such":[42],"as":[43,61],"Automatic":[44],"Speech":[45,51],"Recognition":[46,53],"(ASR),":[47],"Text-to-Speech":[48],"(TTS),":[49],"and":[50,96,119,137,153,158,165],"Emotion":[52],"(SER).":[54],"Current":[55],"evaluation":[56,194],"practices":[57],"are":[58],"also":[59],"limited,":[60],"they":[62],"mainly":[63],"rely":[64],"direct":[66],"testing":[67],"anonymized":[69,139,205],"with":[71,130,180],"pretrained":[72],"models,":[73],"providing":[74],"only":[75],"partial":[77],"view":[78],"utility.":[80],"To":[81,141],"address":[82],"these":[83],"issues,":[84],"we":[85,105,123,147],"propose":[86],"novel":[88],"two-stage":[89],"framework":[90,129,175],"that":[91,134,173],"protects":[92],"both":[93,151],"linguistic":[94],"content":[95,103],"identity":[98],"while":[99,191],"maintaining":[100],"usability.":[101],"For":[102],"privacy,":[104,122],"employ":[106],"generative":[108],"editing":[110],"model":[111],"to":[112,185],"seamlessly":[113],"replace":[114],"personally":[115],"identifiable":[116],"information":[117],"(PII),":[118],"voice":[121],"introduce":[124],"F3-VA,":[125],"flow-matching-based":[127],"three-stage":[132],"design":[133],"produces":[135],"diverse":[136],"distinct":[138],"speakers.":[140],"enable":[142],"more":[144,198],"comprehensive":[145],"assessment,":[146],"evaluate":[148],"using":[150],"acoustic-":[152],"content-based":[154],"speaker":[155],"verification":[156],"metrics,":[157],"assess":[159],"utility":[160,182,203],"training":[162],"ASR,":[163],"TTS,":[164],"SER":[166],"models":[167],"from":[168,187],"scratch.":[169],"Experimental":[170],"results":[171],"show":[172],"our":[174],"achieves":[176],"stronger":[177],"minimal":[181],"degradation":[183],"compared":[184],"baselines":[186],"VoicePrivacy":[189],"Challenge,":[190],"proposed":[193],"protocol":[195],"provides":[196],"realistic":[199],"reflection":[200],"under":[207],"protection.":[209]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-04-22T00:00:00"}
