{"id":"https://openalex.org/W3150653299","doi":"https://doi.org/10.1109/slt48900.2021.9383535","title":"Lightweight Voice Anonymization Based on Data-Driven Optimization of Cascaded Voice Modification Modules","display_name":"Lightweight Voice Anonymization Based on Data-Driven Optimization of Cascaded Voice Modification Modules","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3150653299","doi":"https://doi.org/10.1109/slt48900.2021.9383535","mag":"3150653299"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5024189910","display_name":"Hiroto Kai","orcid":null},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiroto Kai","raw_affiliation_strings":["Tokyo Metropolitan University"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067910092","display_name":"Sayaka Shiota","orcid":"https://orcid.org/0000-0002-2364-068X"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sayaka Shiota","raw_affiliation_strings":["Tokyo Metropolitan University"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015250468","display_name":"Hitoshi Kiya","orcid":"https://orcid.org/0000-0001-8061-3090"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hitoshi Kiya","raw_affiliation_strings":["Tokyo Metropolitan University"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024189910"],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":1.3597,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84141361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"560","last_page":"566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.984000027179718,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.972000002861023,"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":0.8390817642211914},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6801660060882568},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.657015323638916},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6192649006843567},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6027698516845703},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5916962623596191},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.5076228380203247},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.48645469546318054},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4652107357978821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34699106216430664},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.20376557111740112},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1209699809551239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8390817642211914},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6801660060882568},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.657015323638916},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6192649006843567},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6027698516845703},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5916962623596191},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.5076228380203247},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.48645469546318054},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4652107357978821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34699106216430664},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.20376557111740112},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1209699809551239},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W120265440","https://openalex.org/W1437335841","https://openalex.org/W1494198834","https://openalex.org/W2050770647","https://openalex.org/W2128977689","https://openalex.org/W2131241448","https://openalex.org/W2164931619","https://openalex.org/W2168510624","https://openalex.org/W2402146185","https://openalex.org/W2527729766","https://openalex.org/W2806503584","https://openalex.org/W2949676527","https://openalex.org/W2972848589","https://openalex.org/W2973032144","https://openalex.org/W2998572311","https://openalex.org/W3024768724","https://openalex.org/W3043999252","https://openalex.org/W4225585117","https://openalex.org/W4285719527","https://openalex.org/W4395958265","https://openalex.org/W6604875325","https://openalex.org/W6678911119","https://openalex.org/W6712930963","https://openalex.org/W6772349387","https://openalex.org/W6810404315","https://openalex.org/W6864847698"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2114688254","https://openalex.org/W2401827384","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2556771176","https://openalex.org/W2168417340"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,70,116,163],"voice":[6,15,83],"anonymization":[7,84],"framework":[8,85],"based":[9,53,62],"on":[10,54,63],"data-driven":[11,117],"optimization":[12],"of":[13,32,46,75,79,88],"cascaded":[14,124],"modification":[16],"modules.":[17],"With":[18],"increasing":[19],"opportunities":[20],"to":[21,95,162],"use":[22,105],"speech":[23,37,76,120,155],"dialogue":[24],"with":[25,109],"machines":[26],"nowadays,":[27],"research":[28],"regarding":[29],"privacy":[30,50],"protection":[31],"speaker":[33,145],"information":[34],"encapsulated":[35],"in":[36,115,142],"data":[38,111],"is":[39,44,52,121],"attracting":[40],"attention.":[41],"Anonymization,":[42],"which":[43],"one":[45,61],"the":[47,59,97,102,144,154],"methods":[48,108,128],"for":[49,112],"protection,":[51],"signal":[55,92,106,126,164],"processing":[56,107,127],"manners,":[57],"and":[58,77,91,129,135],"other":[60],"machine":[64,89],"learning":[65,90],"ones.":[66],"Both":[67],"approaches":[68,94],"have":[69],"trade":[71,99],"off":[72,100],"between":[73,101],"intelligibility":[74],"degree":[78],"anonymization.":[80],"The":[81,119],"proposed":[82,139],"utilizes":[86],"advantages":[87],"processing-based":[93,165],"find":[96],"optimized":[98],"two.":[103],"We":[104],"training":[110],"optimizing":[113],"hyperparameters":[114],"manner.":[118],"modified":[122],"using":[123,132],"lightweight":[125],"then":[130],"evaluated":[131],"black-box":[133],"ASR":[134],"ASV,":[136],"respectively.":[137],"Our":[138],"method":[140],"succeeded":[141],"deteriorating":[143],"recognition":[146,156],"rate":[147,157],"by":[148,158],"approximately":[149],"22%":[150],"while":[151],"simultaneously":[152],"improved":[153],"over":[159],"3%":[160],"compared":[161],"conventional":[166],"method.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
