{"id":"https://openalex.org/W3092178912","doi":"https://doi.org/10.1109/tifs.2020.3023818","title":"When Automatic Voice Disguise Meets Automatic Speaker Verification","display_name":"When Automatic Voice Disguise Meets Automatic Speaker Verification","publication_year":2020,"publication_date":"2020-09-16","ids":{"openalex":"https://openalex.org/W3092178912","doi":"https://doi.org/10.1109/tifs.2020.3023818","mag":"3092178912"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2020.3023818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2020.3023818","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-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/A5102805800","display_name":"Linlin Zheng","orcid":"https://orcid.org/0000-0002-9034-6472"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linlin Zheng","raw_affiliation_strings":["Laboratory of Intelligent Information Processing, Army Engineering University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9034-6472","affiliations":[{"raw_affiliation_string":"Laboratory of Intelligent Information Processing, Army Engineering University, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009043596","display_name":"Jiakang Li","orcid":"https://orcid.org/0000-0001-7692-841X"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiakang Li","raw_affiliation_strings":["Laboratory of Intelligent Information Processing, Army Engineering University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7692-841X","affiliations":[{"raw_affiliation_string":"Laboratory of Intelligent Information Processing, Army Engineering University, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085248515","display_name":"Meng Sun","orcid":"https://orcid.org/0000-0002-7435-3752"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Sun","raw_affiliation_strings":["Laboratory of Intelligent Information Processing, Army Engineering University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-7435-3752","affiliations":[{"raw_affiliation_string":"Laboratory of Intelligent Information Processing, Army Engineering University, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011581435","display_name":"Xiongwei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongwei Zhang","raw_affiliation_strings":["Laboratory of Intelligent Information Processing, Army Engineering University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4890-0668","affiliations":[{"raw_affiliation_string":"Laboratory of Intelligent Information Processing, Army Engineering University, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"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":"Thomas Fang Zheng","raw_affiliation_strings":["Center for Speech and Language Technologies (CSLT), Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0249-4767","affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies (CSLT), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.086,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.89898959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"16","issue":null,"first_page":"824","last_page":"837"},"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":0.9997000098228455,"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":0.9988999962806702,"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":0.8123871088027954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7255948781967163},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5936734676361084},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.5383350253105164},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4977717697620392},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4585535228252411},{"id":"https://openalex.org/keywords/headphones","display_name":"Headphones","score":0.41619938611984253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36853840947151184},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32264143228530884},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11806315183639526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123871088027954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7255948781967163},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5936734676361084},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.5383350253105164},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4977717697620392},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4585535228252411},{"id":"https://openalex.org/C2781258422","wikidata":"https://www.wikidata.org/wiki/Q186819","display_name":"Headphones","level":2,"score":0.41619938611984253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36853840947151184},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32264143228530884},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11806315183639526},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2020.3023818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2020.3023818","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1122468876","display_name":null,"funder_award_id":"BK20180080","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G1821827784","display_name":"\u9762\u5411\u8bed\u97f3\u8868\u793a\u53ca\u5206\u79bb\u7684\u7ed3\u6784\u5316\u6df1\u5ea6\u5b66\u4e60\u7814\u7a76","funder_award_id":"61471394","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1193200825","https://openalex.org/W1524333225","https://openalex.org/W1596996860","https://openalex.org/W1599112982","https://openalex.org/W1913988943","https://openalex.org/W1945616565","https://openalex.org/W1969952013","https://openalex.org/W1973693762","https://openalex.org/W1997621936","https://openalex.org/W2024903230","https://openalex.org/W2046056978","https://openalex.org/W2072051864","https://openalex.org/W2072764920","https://openalex.org/W2080607798","https://openalex.org/W2081434487","https://openalex.org/W2126762974","https://openalex.org/W2149856110","https://openalex.org/W2150769028","https://openalex.org/W2161603886","https://openalex.org/W2402146185","https://openalex.org/W2471520273","https://openalex.org/W2588445447","https://openalex.org/W2612348557","https://openalex.org/W2745896134","https://openalex.org/W2748488820","https://openalex.org/W2784163702","https://openalex.org/W2800289214","https://openalex.org/W2808631503","https://openalex.org/W2889258566","https://openalex.org/W2890964092","https://openalex.org/W2898564584","https://openalex.org/W2936588983","https://openalex.org/W2936802426","https://openalex.org/W2940070181","https://openalex.org/W2962832278","https://openalex.org/W2963207607","https://openalex.org/W2964013807","https://openalex.org/W2964959870","https://openalex.org/W2967606780","https://openalex.org/W2972986505","https://openalex.org/W3005862564","https://openalex.org/W3103152812","https://openalex.org/W6631362777","https://openalex.org/W6635678660","https://openalex.org/W6640425456","https://openalex.org/W6712930963","https://openalex.org/W6769702557","https://openalex.org/W6831641315"],"related_works":["https://openalex.org/W1519334917","https://openalex.org/W2285322832","https://openalex.org/W2511793349","https://openalex.org/W2506159889","https://openalex.org/W2293832935","https://openalex.org/W2069110031","https://openalex.org/W1911592522","https://openalex.org/W2087669554","https://openalex.org/W3044757496","https://openalex.org/W203970584"],"abstract_inverted_index":{"The":[0,167,203],"technique":[1],"of":[2,12,32,73,85,90,119,145,192,200,244,274],"transforming":[3],"voices":[4,33,157],"in":[5,163,216,235,259,278],"order":[6],"to":[7,43,51,80,114,131,135,188,208,224,230,254],"hide":[8],"the":[9,27,44,117,173,179,189,198,210,232,256,272,275],"real":[10],"identity":[11],"a":[13,71,78,143,160,193],"speaker":[14,57],"is":[15,68,139,228],"called":[16],"voice":[17,22,100,134,174],"disguise,":[18],"among":[19],"which":[20],"automatic":[21,56],"disguise":[23,175,211],"(AVD)":[24],"by":[25,123,141,176,218,237],"modifying":[26],"spectral":[28],"and":[29,55,99,268],"temporal":[30],"characteristics":[31],"with":[34,40,212,267],"miscellaneous":[35],"algorithms":[36],"are":[37,103,111,152],"easily":[38],"conducted":[39,154],"softwares":[41],"accessible":[42],"public.":[45],"AVD":[46,74,120],"has":[47],"posed":[48],"great":[49],"threat":[50],"both":[52],"human":[53],"listening":[54],"verification":[58],"(ASV).":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"have":[64,169],"found":[65],"that":[66],"ASV":[67,109,122,146,265],"not":[69],"only":[70],"victim":[72],"but":[75],"could":[76],"be":[77,252],"tool":[79],"beat":[81],"some":[82],"simple":[83],"types":[84,89],"AVD.":[86],"Firstly,":[87],"three":[88],"AVD,":[91],"pitch":[92,177],"scaling,":[93,178],"vocal":[94],"tract":[95],"length":[96],"normalization":[97],"(VTLN)":[98],"conversion":[101],"(VC),":[102],"introduced":[104],"as":[105],"representative":[106],"methods.":[107],"State-of-the-art":[108],"methods":[110],"subsequently":[112],"utilized":[113],"objectively":[115],"evaluate":[116],"impact":[118],"on":[121,155,264],"equal":[124],"error":[125],"rates":[126],"(EER).":[127],"Moreover,":[128],"an":[129,183,279],"approach":[130,181,205,277],"restore":[132,209,231,255],"disguised":[133,156],"its":[136,220],"original":[137],"version":[138],"proposed":[140,180,195,204,276],"minimizing":[142],"function":[144],"scores":[147],"w.r.t.":[148],"restoration":[149,245,270],"parameters.":[150],"Experiments":[151],"then":[153],"from":[158,222],"Voxceleb,":[159],"dataset":[161],"recorded":[162],"real-world":[164],"noisy":[165],"scenario.":[166],"results":[168],"shown":[170],"that,":[171],"for":[172],"obtains":[182],"EER":[184,191,221],"around":[185],"7%":[186],"comparing":[187],"30%":[190],"recently":[194],"baseline":[196],"using":[197],"ratio":[199],"fundamental":[201],"frequencies.":[202],"generalizes":[206],"well":[207],"nonlinear":[213,257],"frequency":[214],"warping":[215],"VTLN":[217],"reducing":[219],"34.3%":[223],"18.5%.":[225],"However,":[226],"it":[227],"difficult":[229],"source":[233],"speakers":[234],"VC":[236],"our":[238],"approach,":[239],"where":[240],"more":[241],"complex":[242],"forms":[243],"functions":[246],"or":[247],"other":[248],"paralinguistic":[249],"cues":[250],"might":[251],"necessary":[253],"transform":[258],"VC.":[260],"Finally,":[261],"contrastive":[262],"visualization":[263],"features":[266],"without":[269],"illustrate":[271],"role":[273],"intuitive":[280],"way.":[281]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}