{"id":"https://openalex.org/W4408345624","doi":"https://doi.org/10.1109/icassp49660.2025.10889535","title":"Attacking Voice Anonymization Systems with Augmented Feature and Speaker Identity Difference","display_name":"Attacking Voice Anonymization Systems with Augmented Feature and Speaker Identity Difference","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345624","doi":"https://doi.org/10.1109/icassp49660.2025.10889535"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5034912720","display_name":"Yanzhe Zhang","orcid":"https://orcid.org/0009-0001-6253-4273"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanzhe Zhang","raw_affiliation_strings":["Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002945987","display_name":"Zhenqiang Bi","orcid":"https://orcid.org/0000-0002-3368-6139"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhonghao Bi","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062281933","display_name":"Feiyang Xiao","orcid":"https://orcid.org/0000-0001-9359-4554"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyang Xiao","raw_affiliation_strings":["Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014190155","display_name":"Xuefeng Yang","orcid":"https://orcid.org/0000-0002-1022-7183"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Yang","raw_affiliation_strings":["Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104012520","display_name":"Qiaoxi Zhu","orcid":"https://orcid.org/0000-0003-3942-0945"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiaoxi Zhu","raw_affiliation_strings":["Acoustics Lab, University of Technology Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Acoustics Lab, University of Technology Sydney,Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100635946","display_name":"Jian Guan","orcid":"https://orcid.org/0000-0003-3838-5498"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Guan","raw_affiliation_strings":["Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,China","institution_ids":["https://openalex.org/I151727225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9797999858856201,"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":0.9797999858856201,"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/computer-science","display_name":"Computer science","score":0.7599875926971436},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.7569781541824341},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6632083654403687},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6427973508834839},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6210147142410278},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5753687620162964},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4454346001148224},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06695297360420227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599875926971436},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.7569781541824341},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6632083654403687},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6427973508834839},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6210147142410278},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5753687620162964},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4454346001148224},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06695297360420227},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2064364374","https://openalex.org/W2936774411","https://openalex.org/W2995201943","https://openalex.org/W3010925296","https://openalex.org/W3024869864","https://openalex.org/W3205878676","https://openalex.org/W4406461534","https://openalex.org/W4408352614"],"related_works":["https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2144470400","https://openalex.org/W1516392727","https://openalex.org/W2140022733","https://openalex.org/W2911612049"],"abstract_inverted_index":{"This":[0],"study":[1],"focuses":[2],"on":[3],"the":[4,10,34,112,130],"First":[5],"VoicePrivacy":[6],"Attacker":[7],"Challenge":[8],"within":[9],"ICASSP":[11],"2025":[12],"Signal":[13],"Processing":[14],"Grand":[15],"Challenge,":[16],"which":[17],"aims":[18],"to":[19,72,89,102],"develop":[20],"speaker":[21,105],"verification":[22,74],"systems":[23],"capable":[24],"of":[25,42],"determining":[26],"whether":[27],"two":[28],"anonymized":[29,45],"speech":[30,46],"signals":[31],"are":[32,87],"from":[33],"same":[35],"speaker.":[36],"However,":[37],"differences":[38],"between":[39],"feature":[40,64,91],"distributions":[41],"original":[43],"and":[44,66,85,117],"complicate":[47],"this":[48,52],"task.":[49],"To":[50],"address":[51],"challenge,":[53],"we":[54],"propose":[55],"an":[56],"attacker":[57],"system":[58,109],"that":[59],"combines":[60],"Data":[61],"Augmentation":[62],"enhanced":[63,70],"representation":[65],"Speaker":[67],"Identity":[68],"Difference":[69],"classifier":[71],"improve":[73],"performance,":[75],"termed":[76],"DA-SID.":[77],"Specifically,":[78],"data":[79,83],"augmentation":[80],"strategies":[81],"(i.e.,":[82],"fusion":[84],"SpecAugment)":[86],"utilized":[88],"mitigate":[90],"distribution":[92],"gaps,":[93],"while":[94],"probabilistic":[95],"linear":[96],"discriminant":[97],"analysis":[98],"(PLDA)":[99],"is":[100],"employed":[101],"further":[103],"enhance":[104],"identity":[106],"difference.":[107],"Our":[108],"significantly":[110],"outperforms":[111],"baseline,":[113],"demonstrating":[114],"exceptional":[115],"effectiveness":[116],"robustness":[118],"against":[119],"various":[120],"voice":[121],"anonymization":[122],"systems,":[123],"ultimately":[124],"securing":[125],"a":[126],"top-5":[127],"ranking":[128],"in":[129],"challenge.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}