{"id":"https://openalex.org/W4416798432","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248997","title":"Voice Privacy Protection with Adversarial Examples Using Anchor Speaker Embedding","display_name":"Voice Privacy Protection with Adversarial Examples Using Anchor Speaker Embedding","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798432","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248997"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11248997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":null,"display_name":"Shunya Ishikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shunya Ishikawa","raw_affiliation_strings":["The University of Electro-Communications,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108653784","display_name":"Yuki Katsumata","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Katsumata","raw_affiliation_strings":["The University of Electro-Communications,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065514143","display_name":"Toru Nakashika","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["The University of Electro-Communications,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34418239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2063","last_page":"2068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6101999878883362,"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":0.6101999878883362,"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":0.06949999928474426,"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":0.030300000682473183,"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/adversarial-system","display_name":"Adversarial system","score":0.8654999732971191},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5432000160217285},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4968000054359436},{"id":"https://openalex.org/keywords/authentication","display_name":"Authentication (law)","score":0.4722000062465668},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4480000138282776},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4302999973297119},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.41839998960494995},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.399399995803833}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8654999732971191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196000218391418},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6672000288963318},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5432000160217285},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.4722000062465668},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4480000138282776},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.399399995803833},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31940001249313354},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11248997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2129142580","https://openalex.org/W2766219058","https://openalex.org/W2890964092","https://openalex.org/W2962847335","https://openalex.org/W2963362078","https://openalex.org/W2963542245","https://openalex.org/W2964301649","https://openalex.org/W2969542116","https://openalex.org/W2972359262","https://openalex.org/W3024869864","https://openalex.org/W3205878676","https://openalex.org/W4225956675","https://openalex.org/W4312322018","https://openalex.org/W4392904255","https://openalex.org/W4401261782","https://openalex.org/W4402672020","https://openalex.org/W4406417959"],"related_works":[],"abstract_inverted_index":{"Voice":[0],"cloning":[1,69],"technology":[2,24],"has":[3],"advanced":[4],"rapidly":[5],"due":[6],"to":[7,29,41,59,71,129,147,152,156,169],"its":[8],"capacity":[9],"for":[10],"flexible":[11],"speech":[12,73,117,155],"customization,":[13],"with":[14,103],"applications":[15],"spanning":[16],"media":[17],"content":[18],"production":[19],"and":[20,38,136,175],"chatbots.":[21],"However,":[22],"this":[23,110],"also":[25,140],"poses":[26],"significant":[27],"risks":[28],"voice":[30,68],"privacy,":[31],"such":[32,52,61],"as":[33],"fraud":[34],"via":[35],"cloned":[36],"voices":[37],"unauthorized":[39],"access":[40],"speaker":[42,123],"authentication":[43],"systems.":[44],"Recent":[45],"research":[46],"efforts":[47],"have":[48],"focused":[49],"on":[50,98],"preventing":[51],"imitation":[53],"using":[54],"adversarial":[55,64,92,116,158],"examples.":[56],"When":[57],"applied":[58],"speech,":[60,65,93],"examples,":[62],"or":[63],"can":[66],"cause":[67],"models":[70],"synthesize":[72],"signals":[74],"that":[75,144,163],"differ":[76],"from":[77,134],"the":[78,89,105,131,149,153,164,170],"target":[79,106],"voice,":[80],"thereby":[81],"protecting":[82],"audio":[83],"privacy.":[84],"A":[85],"previous":[86],"study":[87],"demonstrated":[88],"effectiveness":[90],"of":[91],"which":[94],"is":[95,167],"optimized":[96],"based":[97],"a":[99,114,126,142],"simple":[100],"loss":[101,127],"function":[102,128],"only":[104],"speaker's":[107],"embedding.":[108],"In":[109],"study,":[111],"we":[112],"propose":[113,141],"novel":[115],"generation":[118],"method,":[119],"incorporating":[120],"an":[121],"anchor":[122],"embedding":[124],"into":[125],"enhance":[130],"protective":[132],"performance":[133],"objective":[135,174],"subjective":[137,176],"perspectives.":[138],"We":[139],"method":[143,166,172],"uses":[145],"Adam":[146],"optimize":[148],"noise":[150],"added":[151],"original":[154],"generate":[157],"speech.":[159],"Experimental":[160],"results":[161],"indicate":[162],"proposed":[165],"superior":[168],"conventional":[171],"in":[173],"metrics.":[177]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}