{"id":"https://openalex.org/W7107864583","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249401","title":"Investigation of Perception Inconsistency in Speaker Embedding for Asynchronous Voice Anonymization","display_name":"Investigation of Perception Inconsistency in Speaker Embedding for Asynchronous Voice Anonymization","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7107864583","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249401"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249401","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":"Rui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liping Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Chen","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kong Aik Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhengpeng Zha","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengpeng Zha","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhenhua Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Ling","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2074","last_page":"2079"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9013000130653381,"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":0.9013000130653381,"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/T10863","display_name":"Voice and Speech Disorders","score":0.03959999978542328,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.009600000455975533,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.8068000078201294},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7544999718666077},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6848000288009644},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.6025000214576721},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46299999952316284},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.45019999146461487},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.39149999618530273}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8068000078201294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681000232696533},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7544999718666077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7325999736785889},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6848000288009644},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6025000214576721},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.45019999146461487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4043000042438507},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C2777072894","wikidata":"https://www.wikidata.org/wiki/Q4812204","display_name":"Asynchronous learning","level":5,"score":0.3018999993801117},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.2687999904155731}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249401","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":[{"id":"https://openalex.org/G2883670753","display_name":null,"funder_award_id":"U23B2053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4872633592","display_name":null,"funder_award_id":"2024YFE0217200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5333787274","display_name":null,"funder_award_id":"WK2100000043","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2037942310","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2972848589","https://openalex.org/W3024869864","https://openalex.org/W3043999252","https://openalex.org/W3163421828","https://openalex.org/W4225322394","https://openalex.org/W4372260053","https://openalex.org/W4380364830","https://openalex.org/W4385823264","https://openalex.org/W4402111485"],"related_works":[],"abstract_inverted_index":{"Given":[0],"the":[1,7,22,27,31,39,43,69,76,97,101,122],"speech":[2,70,80],"generation":[3,71,81],"framework":[4],"that":[5],"represents":[6],"speaker":[8,23,40,44,66,98],"attribute":[9,41,99],"with":[10],"an":[11,107],"embedding":[12,24,45,67],"vector,":[13],"asynchronous":[14,52,108],"voice":[15,53,109],"anonymization":[16,110],"can":[17,127],"be":[18,128],"achieved":[19],"by":[20],"modifying":[21],"derived":[25],"from":[26],"original":[28],"speech.":[29,103],"However,":[30],"inconsistency":[32,62],"between":[33],"machine":[34,89,123],"and":[35,78],"human":[36,94,116],"perceptions":[37],"of":[38,96],"within":[42],"remains":[46],"unexplored,":[47],"limiting":[48],"its":[49,93],"performance":[50],"in":[51,68,100,130],"anonymization.":[54],"To":[55],"this":[56,58,61],"end,":[57],"study":[59],"investigates":[60],"via":[63],"modifications":[64],"to":[65],"process.":[72],"Experiments":[73],"conducted":[74],"on":[75],"FACodec":[77],"Diff-HierVC":[79],"models":[82],"discover":[83],"a":[84],"subspace":[85],"whose":[86],"removal":[87],"alters":[88],"perception":[90,95,117],"while":[91,120],"preserving":[92],"generated":[102],"With":[104],"these":[105],"findings,":[106],"is":[111],"developed,":[112],"achieving":[113],"100":[114],"%":[115],"preservation":[118],"rate":[119],"obscuring":[121],"perception.":[124],"Audio":[125],"samples":[126],"found":[129],"https://voiceprivacy.github.io/speaker-embedding-eigen-decomposition/.":[131]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}