{"id":"https://openalex.org/W4388118603","doi":"https://doi.org/10.23919/eusipco58844.2023.10289777","title":"Canonical Voice Conversion and Dual-Channel Processing for Improved Voice Privacy of Speech Recognition Data","display_name":"Canonical Voice Conversion and Dual-Channel Processing for Improved Voice Privacy of Speech Recognition Data","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388118603","doi":"https://doi.org/10.23919/eusipco58844.2023.10289777"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10289777","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10289777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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/A5108774400","display_name":"Dushyant Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dushyant Sharma","raw_affiliation_strings":["Nuance Communications Inc.,USA","Nuance Communications Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc.,USA","institution_ids":["https://openalex.org/I4210125787"]},{"raw_affiliation_string":"Nuance Communications Inc., USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015387266","display_name":"Francesco Nespoli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Francesco Nespoli","raw_affiliation_strings":["Nuance Communications Inc.,USA","Imperial College London, UK","Nuance Communications Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc.,USA","institution_ids":["https://openalex.org/I4210125787"]},{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Nuance Communications Inc., USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rong Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Rong Gong","raw_affiliation_strings":["Nuance Communications GmbH,Austria","Nuance Communications GmbH, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications GmbH,Austria","institution_ids":["https://openalex.org/I1292318990"]},{"raw_affiliation_string":"Nuance Communications GmbH, Austria","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Imperial College London,UK","Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57210246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"70"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.8268764019012451},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.770626425743103},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.656166136264801},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6510457396507263},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5512703657150269},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5448174476623535},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44363266229629517},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08928048610687256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8268764019012451},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.770626425743103},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.656166136264801},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6510457396507263},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5512703657150269},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5448174476623535},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44363266229629517},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08928048610687256}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10289777","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10289777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1589137271","https://openalex.org/W1620899341","https://openalex.org/W2748488820","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2951082691","https://openalex.org/W2964054038","https://openalex.org/W2998572311","https://openalex.org/W3010925296","https://openalex.org/W3024869864","https://openalex.org/W3095173472","https://openalex.org/W3167533889","https://openalex.org/W3198134544","https://openalex.org/W3207599282","https://openalex.org/W4210970267","https://openalex.org/W4226279385","https://openalex.org/W4372260098","https://openalex.org/W6796464841","https://openalex.org/W6805710207"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,7,50,57,121,131,147,158],"need":[4],"for":[5,67],"enhancing":[6],"privacy":[8,139],"of":[9,59,99,123,149],"test":[10],"data":[11,94,102,110],"in":[12,105,138,146,167],"a":[13,32,64,79,83,114,124,135,143,164,171],"deployed":[14],"automatic":[15,151],"speech":[16,101],"recognition":[17],"(ASR)":[18],"system":[19,119],"so":[20],"that":[21,130],"what":[22],"was":[23],"said":[24,30],"cannot":[25],"be":[26,42],"linked":[27],"to":[28,44,48,82,88,120,170],"who":[29],"it,":[31],"process":[33],"we":[34],"describe":[35],"as":[36,140,161],"acoustic":[37],"de-identification.":[38],"Existing":[39],"techniques":[40],"can":[41],"used":[43,104],"modify":[45],"voice":[46,74,109,116,122],"characteristics":[47],"make":[49],"speaker":[51,152],"identity":[52],"unrecognizable,":[53],"but":[54],"normally":[55],"at":[56],"expense":[58],"ASR":[60,69,91,159],"performance.":[61],"We":[62,128],"present":[63],"novel":[65],"approach":[66,133],"improving":[68,157],"performance":[70],"on":[71,179],"acoustically":[72,180],"de-identified":[73,112,181],"data.":[75],"Our":[76],"method":[77],"exploits":[78],"dual-channel":[80],"input":[81],"self-attention":[84],"channel":[85,173],"combinator":[86],"front-end":[87],"an":[89,150],"end-to-end":[90],"system,":[92,154],"and":[93],"augmentation,":[95],"where":[96],"some":[97],"amount":[98],"original":[100],"is":[103,111],"model":[106,174,176],"training.":[107],"The":[108],"by":[113,142,163],"zero-shot":[115],"style":[117],"transfer":[118],"registered,":[125],"canonical":[126],"speaker.":[127],"show":[129],"proposed":[132],"achieves":[134],"significant":[136],"improvement":[137],"demonstrated":[141,162],"10x":[144],"increase":[145],"EER":[148],"verification":[153],"while":[155],"also":[156],"accuracy":[160],"18.3%":[165],"reduction":[166],"WER":[168],"relative":[169],"single":[172],"baseline":[175],"when":[177],"tested":[178],"speech.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}