{"id":"https://openalex.org/W4408347270","doi":"https://doi.org/10.1109/icassp49660.2025.10889709","title":"Why disentanglement-based speaker anonymization systems fail at preserving emotions?","display_name":"Why disentanglement-based speaker anonymization systems fail at preserving emotions?","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347270","doi":"https://doi.org/10.1109/icassp49660.2025.10889709"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889709","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/A5019098450","display_name":"\u00dcnal Ege Gaznepoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"\u00dcnal Ege Gaznepoglu","raw_affiliation_strings":["Friedrich-Alexander-University,International Audio Laboratories Erlangen,Erlangen-Nürnberg,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-University,International Audio Laboratories Erlangen,Erlangen-Nürnberg,Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101869282","display_name":"Nils Peters","orcid":"https://orcid.org/0000-0001-6758-4491"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Nils Peters","raw_affiliation_strings":["Trinity College Dublin,Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Trinity College Dublin,Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.346,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90285525,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"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":0.902899980545044,"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":0.902899980545044,"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":0.822780966758728},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5623403191566467},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5185164213180542},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2203054130077362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822780966758728},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5623403191566467},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5185164213180542},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2203054130077362}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889709","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":0.7200000286102295,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2096429026","https://openalex.org/W2146334809","https://openalex.org/W2972848589","https://openalex.org/W3024869864","https://openalex.org/W3081192838","https://openalex.org/W3162366763","https://openalex.org/W3209059054","https://openalex.org/W3210530853","https://openalex.org/W4221152846","https://openalex.org/W4307323391","https://openalex.org/W4319862652","https://openalex.org/W4372260248","https://openalex.org/W4375869259","https://openalex.org/W4382202681","https://openalex.org/W4385822420","https://openalex.org/W4385822773","https://openalex.org/W4386557792","https://openalex.org/W4386712586","https://openalex.org/W4392902630","https://openalex.org/W4392902635","https://openalex.org/W4392909842","https://openalex.org/W4410065299","https://openalex.org/W6750489868","https://openalex.org/W6783867762","https://openalex.org/W6838843145","https://openalex.org/W6855439139","https://openalex.org/W6869940612"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2140022733","https://openalex.org/W2090976131","https://openalex.org/W1516392727"],"abstract_inverted_index":{"Disentanglement-based":[0],"speaker":[1,13,49,70,94],"anonymization":[2,71],"involves":[3],"decomposing":[4],"speech":[5],"into":[6],"a":[7,17,20,64,68,98,106,114],"semantically":[8],"meaningful":[9],"representation,":[10],"altering":[11],"the":[12,55,75,81,85,91],"embedding,":[14],"and":[15,44],"resynthesizing":[16],"waveform":[18],"using":[19],"neural":[21],"vocoder.":[22],"State-of-the-art":[23],"systems":[24],"of":[25,46,54,67,87],"this":[26,60],"kind":[27],"are":[28,103],"known":[29],"to":[30,73],"remove":[31],"emotion":[32,127,145],"information.":[33],"Possible":[34],"reasons":[35],"include":[36],"mode":[37],"collapse":[38],"in":[39,90,105],"GAN-based":[40],"vocoders,":[41],"unintended":[42],"modeling":[43],"modification":[45],"emotions":[47],"through":[48],"embeddings,":[50],"or":[51],"excessive":[52],"sanitization":[53],"intermediate":[56],"representation":[57],"(IR).":[58],"In":[59],"paper,":[61],"we":[62,118,136],"conduct":[63],"comprehensive":[65],"evaluation":[66,129],"state-of-the-art":[69],"system":[72],"understand":[74],"underlying":[76],"causes.":[77],"We":[78],"conclude":[79,137],"that":[80,120,138],"main":[82],"reason":[83],"is":[84,148],"lack":[86],"emotion-related":[88],"information":[89],"IR.":[92],"The":[93,109],"embeddings":[95],"also":[96],"have":[97],"high":[99],"impact,":[100],"if":[101],"they":[102],"learned":[104],"generative":[107],"context.":[108],"vocoder\u2019s":[110],"out-of-distribution":[111],"performance":[112,147],"has":[113],"smaller":[115],"impact.":[116],"Additionally,":[117],"discovered":[119],"synthesis":[121],"artifacts":[122],"increase":[123],"spectral":[124],"kurtosis,":[125],"biasing":[126],"recognition":[128,146],"towards":[130],"classifying":[131],"utterances":[132],"as":[133],"angry.":[134],"Therefore,":[135],"reporting":[139],"unweighted":[140],"average":[141],"recall":[142],"alone":[143],"for":[144],"suboptimal.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}