{"id":"https://openalex.org/W4372260098","doi":"https://doi.org/10.1109/icassp49357.2023.10095173","title":"A Speech Representation Anonymization Framework via Selective Noise Perturbation","display_name":"A Speech Representation Anonymization Framework via Selective Noise Perturbation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260098","doi":"https://doi.org/10.1109/icassp49357.2023.10095173"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103277708","display_name":"Minh Tran","orcid":"https://orcid.org/0009-0004-2391-3563"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minh Tran","raw_affiliation_strings":["University of Southern California,Institute for Creative Technologies,Los Angeles,USA","Institute for Creative Technologies, University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Institute for Creative Technologies,Los Angeles,USA","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]},{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024169758","display_name":"Mohammad Soleymani","orcid":"https://orcid.org/0000-0002-5873-1434"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Soleymani","raw_affiliation_strings":["University of Southern California,Institute for Creative Technologies,Los Angeles,USA","Institute for Creative Technologies, University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Institute for Creative Technologies,Los Angeles,USA","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]},{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103277708"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210087747"],"apc_list":null,"apc_paid":null,"fwci":1.0577,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80843992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9962999820709229,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.8265196084976196},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6739161610603333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6028931736946106},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5252171158790588},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45717647671699524},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.41086453199386597},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32387131452560425},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11669117212295532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8265196084976196},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6739161610603333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6028931736946106},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5252171158790588},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45717647671699524},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.41086453199386597},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32387131452560425},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11669117212295532},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6800000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W120265440","https://openalex.org/W1494198834","https://openalex.org/W2146334809","https://openalex.org/W2293829681","https://openalex.org/W2726515241","https://openalex.org/W2784163702","https://openalex.org/W2890964092","https://openalex.org/W2953900859","https://openalex.org/W2972584841","https://openalex.org/W2997604315","https://openalex.org/W3018464563","https://openalex.org/W3024768724","https://openalex.org/W3036601975","https://openalex.org/W3043999252","https://openalex.org/W3103152812","https://openalex.org/W3123483592","https://openalex.org/W3150653299","https://openalex.org/W3197008493","https://openalex.org/W3197580070","https://openalex.org/W4205228770","https://openalex.org/W4210675298","https://openalex.org/W4225585117","https://openalex.org/W4293861706","https://openalex.org/W4310650179","https://openalex.org/W4385245566","https://openalex.org/W4395958265","https://openalex.org/W6739575509","https://openalex.org/W6739901393","https://openalex.org/W6740167877","https://openalex.org/W6780218876","https://openalex.org/W6789567290","https://openalex.org/W6810404315","https://openalex.org/W6864847698"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"Privacy":[0],"and":[1,19,125,131],"security":[2],"are":[3],"major":[4],"concerns":[5],"when":[6],"communicating":[7],"speech":[8,16,20,27,60,78,99,153],"signals":[9],"to":[10,37,58,87,142,151,176],"cloud":[11],"services":[12],"such":[13],"as":[14],"automatic":[15],"recognition":[17,22],"(ASR)":[18],"emotion":[21],"(SER).":[23],"Existing":[24],"solutions":[25],"for":[26,129],"anonymization":[28,79,154],"mainly":[29],"focus":[30],"on":[31,115],"voice":[32,35],"conversion":[33],"or":[34,50,146],"modification":[36],"convert":[38],"a":[39,77,88,97,106,144,178],"raw":[40],"utterance":[41],"into":[42],"another":[43],"one":[44],"with":[45,105],"similar":[46],"content":[47],"but":[48],"different,":[49],"no,":[51],"identity-related":[52],"information.":[53],"However,":[54],"an":[55],"alternative":[56],"approach":[57,139],"share":[59],"data":[61],"under":[62],"the":[63,92,152,157,162,168],"form":[64],"of":[65,91,165,171,181],"privacy-preserving":[66],"representation":[67],"has":[68],"been":[69],"largely":[70],"under-explored.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"propose":[76],"framework":[80,114,175],"that":[81,137],"achieves":[82],"privacy":[83,130],"via":[84],"noise":[85],"perturbation":[86,172],"selected":[89],"subset":[90,102],"high-utility":[93],"representations":[94],"extracted":[95],"using":[96],"pre-trained":[98],"encoder.":[100],"The":[101],"is":[103,140],"chosen":[104],"Transformer-based":[107],"privacy-risk":[108],"saliency":[109],"estimator.":[110],"We":[111],"validate":[112],"our":[113,138,174],"four":[116],"tasks,":[117],"namely,":[118],"Automatic":[119],"Speaker":[120],"Verification":[121],"(ASV),":[122],"ASR,":[123],"SER":[124],"Intent":[126],"Classification":[127],"(IC)":[128],"utility":[132,149],"assessment.":[133],"Experimental":[134],"results":[135],"show":[136],"able":[141],"achieve":[143],"competitive,":[145],"even":[147],"superior,":[148],"compared":[150],"baselines":[155],"from":[156],"VoicePrivacy2022":[158],"Challenges,":[159],"while":[160],"maintaining":[161],"same":[163],"level":[164],"privacy.":[166],"Moreover,":[167],"easily-controlled":[169],"amount":[170],"allows":[173],"have":[177],"flexible":[179],"range":[180],"privacy-utility":[182],"trade-offs":[183],"without":[184],"re-training":[185],"any":[186],"component.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}