{"id":"https://openalex.org/W4390479048","doi":"https://doi.org/10.1145/3595916.3626367","title":"GhostVec: A New Threat to Speaker Privacy of End-to-End Speech Recognition System","display_name":"GhostVec: A New Threat to Speaker Privacy of End-to-End Speech Recognition System","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390479048","doi":"https://doi.org/10.1145/3595916.3626367"},"language":"en","primary_location":{"id":"doi:10.1145/3595916.3626367","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626367","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626367","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626367","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103093817","display_name":"Xiaojiao Chen","orcid":"https://orcid.org/0000-0002-5458-7025"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojiao Chen","raw_affiliation_strings":["Xinjiang University\\t, CN"],"raw_orcid":"https://orcid.org/0000-0002-5458-7025","affiliations":[{"raw_affiliation_string":"Xinjiang University\\t, CN","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT), JP"],"raw_orcid":"https://orcid.org/0000-0001-7636-3797","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), JP","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067208985","display_name":"Jiyi Li","orcid":"https://orcid.org/0000-0003-4997-3850"},"institutions":[{"id":"https://openalex.org/I66906201","display_name":"University of Yamanashi","ror":"https://ror.org/059x21724","country_code":"JP","type":"education","lineage":["https://openalex.org/I66906201"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiyi Li","raw_affiliation_strings":["University of Yamanashi, JP"],"raw_orcid":"https://orcid.org/0000-0003-4997-3850","affiliations":[{"raw_affiliation_string":"University of Yamanashi, JP","institution_ids":["https://openalex.org/I66906201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082946615","display_name":"Yang Cao","orcid":"https://orcid.org/0000-0002-6424-8633"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yang Cao","raw_affiliation_strings":["Hokkaido University, JP"],"raw_orcid":"https://orcid.org/0000-0002-6424-8633","affiliations":[{"raw_affiliation_string":"Hokkaido University, JP","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University, CN"],"raw_orcid":"https://orcid.org/0000-0001-6604-0951","affiliations":[{"raw_affiliation_string":"Xinjiang University, CN","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049944728","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4076-7479"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Tsinghua University, CN"],"raw_orcid":"https://orcid.org/0000-0003-4076-7479","affiliations":[{"raw_affiliation_string":"Tsinghua University, CN","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.8365633487701416},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.74772047996521},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7470171451568604},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6928942799568176},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5312286019325256},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5154803395271301},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.42854446172714233},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4259507656097412},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41915541887283325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32563114166259766},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16864654421806335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8365633487701416},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.74772047996521},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7470171451568604},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6928942799568176},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5312286019325256},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5154803395271301},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.42854446172714233},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4259507656097412},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41915541887283325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32563114166259766},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16864654421806335},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595916.3626367","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626367","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626367","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3595916.3626367","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626367","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626367","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4390204761","display_name":null,"funder_award_id":"JP23K11227","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5208785282","display_name":"Learning Reliable Deep Models from Noise Labels by Crowdsourcing","funder_award_id":"23K28092","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390479048.pdf","grobid_xml":"https://content.openalex.org/works/W4390479048.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2535690855","https://openalex.org/W2890964092","https://openalex.org/W2892009249","https://openalex.org/W2964099675","https://openalex.org/W3112689365","https://openalex.org/W3112702554"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Speaker":[0],"adaptation":[1],"systems":[2,8],"face":[3],"privacy":[4],"concerns,":[5],"for":[6],"such":[7],"are":[9],"trained":[10],"on":[11,36,134],"private":[12],"datasets":[13],"and":[14,44,49,89,106],"often":[15],"overfitting.":[16],"This":[17],"paper":[18],"demonstrates":[19],"that":[20,97],"an":[21,59],"attacker":[22],"can":[23],"extract":[24,54],"speaker":[25,38,56,66],"information":[26,39,57],"by":[27],"querying":[28],"speaker-adapted":[29],"speech":[30,131],"recognition":[31,132],"(ASR)":[32],"systems.":[33],"We":[34,120],"focus":[35],"the":[37,55,98,114,117,122],"of":[40,101,116],"a":[41,47,74],"transformer-based":[42],"ASR":[43,61],"propose":[45],"GhostVec,":[46],"simple":[48],"efficient":[50],"attack":[51],"method":[52],"to":[53,128],"from":[58],"encoder-decoder-based":[60],"system":[62,68],"without":[63],"any":[64],"external":[65],"verification":[67],"or":[69],"natural":[70],"human":[71],"voice":[72],"as":[73],"reference.":[75],"To":[76],"make":[77],"our":[78],"results":[79,95],"quantitative,":[80],"we":[81],"pre-process":[82],"GhostVec":[83,102],"using":[84],"singular":[85],"value":[86],"decomposition":[87],"(SVD)":[88],"synthesize":[90],"it":[91],"into":[92],"waveform.":[93],"Experiment":[94],"show":[96],"synthesized":[99],"audio":[100],"reaches":[103],"10.83%":[104],"EER":[105],"0.47":[107],"minDCF":[108],"with":[109],"target":[110],"speakers,":[111],"which":[112],"suggests":[113],"effectiveness":[115],"proposed":[118],"method.":[119],"hope":[121],"preliminary":[123],"discovery":[124],"in":[125],"this":[126],"study":[127],"catalyze":[129],"future":[130],"research":[133],"privacy-preserving":[135],"topics.":[136]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}