{"id":"https://openalex.org/W4319862433","doi":"https://doi.org/10.1109/slt54892.2023.10022601","title":"Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy","display_name":"Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862433","doi":"https://doi.org/10.1109/slt54892.2023.10022601"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022601","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5064340157","display_name":"Sarina Meyer","orcid":"https://orcid.org/0009-0004-1117-4783"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sarina Meyer","raw_affiliation_strings":["Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","Institute for Natural Language Processing (IMS), University of Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091791731","display_name":"Pascal Tilli","orcid":"https://orcid.org/0009-0001-7503-1413"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pascal Tilli","raw_affiliation_strings":["Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","Institute for Natural Language Processing (IMS), University of Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081451455","display_name":"Pavel Denisov","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pavel Denisov","raw_affiliation_strings":["Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","Institute for Natural Language Processing (IMS), University of Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078880407","display_name":"Florian Lux","orcid":"https://orcid.org/0000-0003-4325-5129"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Lux","raw_affiliation_strings":["Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","Institute for Natural Language Processing (IMS), University of Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082226616","display_name":"Julia Koch","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julia Koch","raw_affiliation_strings":["Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","Institute for Natural Language Processing (IMS), University of Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020700841","display_name":"Ngoc Thang Vu","orcid":"https://orcid.org/0000-0001-7893-9147"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ngoc Thang Vu","raw_affiliation_strings":["Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","Institute for Natural Language Processing (IMS), University of Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Institute for Natural Language Processing (IMS), University of Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5064340157"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":3.4126,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93556701,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"912","last_page":"919"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9977999925613403,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9955000281333923,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8392452001571655},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6023279428482056},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5629509687423706},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5591073632240295},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5588657259941101},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5567001104354858},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5554218292236328},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.48415762186050415},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4592890441417694},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4183996021747589},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.36049675941467285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31028300523757935},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.23058152198791504},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.17431816458702087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392452001571655},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6023279428482056},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5629509687423706},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5591073632240295},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5588657259941101},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5567001104354858},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5554218292236328},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.48415762186050415},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4592890441417694},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4183996021747589},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.36049675941467285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31028300523757935},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.23058152198791504},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.17431816458702087},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022601","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2194775991","https://openalex.org/W2726515241","https://openalex.org/W2766219058","https://openalex.org/W2772024149","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2972359262","https://openalex.org/W2981087920","https://openalex.org/W2991440249","https://openalex.org/W2995584712","https://openalex.org/W2998572311","https://openalex.org/W3024768724","https://openalex.org/W3024869864","https://openalex.org/W3043999252","https://openalex.org/W3049278490","https://openalex.org/W3081871358","https://openalex.org/W3092028330","https://openalex.org/W3094544164","https://openalex.org/W3095232705","https://openalex.org/W3097777922","https://openalex.org/W3150653299","https://openalex.org/W3166661385","https://openalex.org/W3167533889","https://openalex.org/W3177624059","https://openalex.org/W3184252821","https://openalex.org/W3196321886","https://openalex.org/W3196623473","https://openalex.org/W3197008493","https://openalex.org/W3197790422","https://openalex.org/W3212903180","https://openalex.org/W3216758611","https://openalex.org/W4221114270","https://openalex.org/W4221152846","https://openalex.org/W4225585117","https://openalex.org/W4287601674","https://openalex.org/W4295521014","https://openalex.org/W4296069300","https://openalex.org/W4320013936","https://openalex.org/W4387941731","https://openalex.org/W6735913928","https://openalex.org/W6741832134","https://openalex.org/W6746490506","https://openalex.org/W6752378368","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6795812529","https://openalex.org/W6843630785"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W2888032422","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"In":[0,63],"order":[1],"to":[2,53,68,107],"protect":[3],"the":[4,14,21,40,47,124],"privacy":[5,103],"of":[6,16,35,39,46,102,123],"speech":[7,24],"data,":[8],"speaker":[9,18,74],"anonymization":[10],"aims":[11],"for":[12,42],"hiding":[13],"identity":[15],"a":[17,30,77,93],"by":[19,72],"changing":[20],"voice":[22],"in":[23,49,100],"recordings.":[25,126],"This":[26],"typically":[27],"comes":[28],"with":[29,81],"privacy-utility":[31],"trade-off":[32],"between":[33],"protection":[34],"individuals":[36],"and":[37,104,111,118],"usability":[38],"data":[41],"downstream":[43],"applications.":[44],"One":[45],"challenges":[48],"this":[50,64,70],"context":[51],"is":[52],"create":[54],"non-existent":[55],"voices":[56],"that":[57],"sound":[58],"as":[59,61,84],"natural":[60],"possible.":[62],"work,":[65],"we":[66,96],"propose":[67],"tackle":[69],"issue":[71],"generating":[73],"embeddings":[75,91],"using":[76],"generative":[78],"adversarial":[79],"network":[80],"Wasserstein":[82],"distance":[83],"cost":[85],"function.":[86],"By":[87],"incorporating":[88],"these":[89],"artificial":[90],"into":[92],"speech-to-text-to-speech":[94],"pipeline,":[95],"outperform":[97],"previous":[98],"approaches":[99],"terms":[101],"utility.":[105],"According":[106],"standard":[108],"objective":[109],"metrics":[110],"human":[112],"evaluation,":[113],"our":[114],"approach":[115],"generates":[116],"intelligible":[117],"content-preserving":[119],"yet":[120],"privacy-protecting":[121],"versions":[122],"original":[125]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}