{"id":"https://openalex.org/W7127455985","doi":"https://doi.org/10.1109/ism66958.2025.00040","title":"Dialogue-Pseudo: A Speaker Pseudonymization Framework for Privacy Protection in Dialogue Speech Data","display_name":"Dialogue-Pseudo: A Speaker Pseudonymization Framework for Privacy Protection in Dialogue Speech Data","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7127455985","doi":"https://doi.org/10.1109/ism66958.2025.00040"},"language":null,"primary_location":{"id":"doi:10.1109/ism66958.2025.00040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ism66958.2025.00040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Symposium on Multimedia (ISM)","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/A5104156086","display_name":"Aoi Ito","orcid":null},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aoi Ito","raw_affiliation_strings":["Graduate School of Computer and Information Sciences, Hosei University,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Computer and Information Sciences, Hosei University,Tokyo,Japan","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082263555","display_name":"Katunobu Itou","orcid":null},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katunobu Itou","raw_affiliation_strings":["Hosei University,Faculty of Computer and Information Sciences,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hosei University,Faculty of Computer and Information Sciences,Tokyo,Japan","institution_ids":["https://openalex.org/I204291657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80981968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.3059999942779541,"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":0.3059999942779541,"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/T12031","display_name":"Speech and dialogue systems","score":0.2840999960899353,"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/T10028","display_name":"Topic Modeling","score":0.10719999670982361,"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/prosody","display_name":"Prosody","score":0.7070000171661377},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4810999929904938},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.4805999994277954},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.3982999920845032},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.36550000309944153},{"id":"https://openalex.org/keywords/speech-act","display_name":"Speech act","score":0.3357999920845032},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.3237999975681305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498000264167786},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7070000171661377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.602400004863739},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.4805999994277954},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4426000118255615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40389999747276306},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.36550000309944153},{"id":"https://openalex.org/C2984865316","wikidata":"https://www.wikidata.org/wiki/Q25481968","display_name":"Speech act","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3237999975681305},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.26420000195503235}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ism66958.2025.00040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ism66958.2025.00040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Symposium on Multimedia (ISM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5314353108406067,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2471520273","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2951082691","https://openalex.org/W2972848589","https://openalex.org/W3212886388","https://openalex.org/W4210970267","https://openalex.org/W4385734287","https://openalex.org/W4385822353","https://openalex.org/W4399972440","https://openalex.org/W4400770760","https://openalex.org/W4402826865","https://openalex.org/W4408897700","https://openalex.org/W4409058573"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"\u201cDialogue-Pseudo\u201d,":[2],"a":[3,14,18,64,133],"dialogue-aware":[4,19],"pseudonymization":[5,142],"framework":[6],"that":[7,46,115,140],"(i)":[8],"maps":[9],"each":[10],"real":[11],"speaker":[12,77],"to":[13,22,36,88,136,146],"distinct":[15],"pseudo-speaker":[16,65],"via":[17],"Partition-Assignment-Selection":[20],"procedure":[21],"preserve":[23],"inter-speaker":[24],"separability,":[25],"(ii)":[26],"replaces":[27],"personally":[28],"identifiable":[29],"information":[30],"with":[31,63,155],"syllable-":[32],"and":[33,40,54,111,124,149],"accent-matched":[34],"surrogates":[35],"maintain":[37],"phonorhythmic":[38],"timing,":[39],"(iii)":[41],"applies":[42],"bounded":[43],"prosody":[44],"control":[45],"normalizes":[47],"global":[48],"pitch/energy":[49],"while":[50],"preserving":[51],"relative":[52],"contours":[53],"turn-taking":[55],"cues.":[56],"Experiments":[57],"on":[58],"the":[59,122,156],"RWCP":[60],"conversational":[61],"corpus":[62],"pool":[66],"derived":[67],"from":[68,85,120,125],"Common":[69],"Voice":[70],"show":[71],"improved":[72],"privacy":[73],"under":[74],"an":[75],"ECAPA-TDNN":[76],"verification":[78],"model:":[79],"Equal":[80],"Error":[81],"Rate":[82],"(EER)":[83],"increases":[84],"37.38%":[86],"(original)":[87],"<tex":[89],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[90],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{4":[91],"2.":[92],"2":[93,94],"\\%}$</tex>":[95],"(pseudonymized).":[96],"Prosody-oriented":[97],"statistics":[98],"(F0":[99],"mean/variance,":[100],"RMS":[101],"energy,":[102],"pause":[103],"ratio,":[104],"turn":[105],"length)":[106],"remain":[107],"close":[108],"across":[109],"conditions,":[110],"UMAP":[112],"visualizations":[113],"indicate":[114],"pseudo-speakers":[116],"are":[117],"well":[118],"separated":[119],"both":[121],"sources":[123],"one":[126],"another.":[127],"These":[128],"results":[129],"support":[130],"Dialogue-Pseudo":[131],"as":[132],"practical":[134],"approach":[135],"privacy-preserving":[137],"dialogue":[138],"analytics":[139],"extends":[141],"beyond":[143],"timbre":[144],"conversion":[145],"dialogue-relevant":[147],"linguistic":[148],"prosodic":[150],"cues,":[151],"thereby":[152],"balancing":[153],"unlinkability":[154],"retention":[157],"of":[158],"task-critical":[159],"information.":[160]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-04T00:00:00"}