{"id":"https://openalex.org/W3146945401","doi":"https://doi.org/10.1109/slt48900.2021.9383558","title":"Detection and Evaluation of Human and Machine Generated Speech in Spoofing Attacks on Automatic Speaker Verification Systems","display_name":"Detection and Evaluation of Human and Machine Generated Speech in Spoofing Attacks on Automatic Speaker Verification Systems","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3146945401","doi":"https://doi.org/10.1109/slt48900.2021.9383558","mag":"3146945401"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383558","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/A5102873084","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0003-0348-2546"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yang Gao","raw_affiliation_strings":["Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108846913","display_name":"Jiachen Lian","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiachen Lian","raw_affiliation_strings":["Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102775511","display_name":"Rita Singh","orcid":"https://orcid.org/0000-0003-3743-0162"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rita Singh","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102873084"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.3115,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90090071,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"544","last_page":"551"},"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":0.9994999766349792,"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":0.9975000023841858,"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/spoofing-attack","display_name":"Spoofing attack","score":0.8431497812271118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8252224922180176},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6883536577224731},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5351553559303284},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5197467803955078},{"id":"https://openalex.org/keywords/human-voice","display_name":"Human voice","score":0.4806710183620453},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.4411580562591553},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4287929832935333},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.424477219581604},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.41161614656448364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2826090157032013},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.16297966241836548}],"concepts":[{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.8431497812271118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252224922180176},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6883536577224731},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5351553559303284},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5197467803955078},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.4806710183620453},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.4411580562591553},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4287929832935333},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.424477219581604},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.41161614656448364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2826090157032013},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.16297966241836548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383558","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":0.8199999928474426,"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":36,"referenced_works":["https://openalex.org/W1738371459","https://openalex.org/W2129521125","https://openalex.org/W2176804518","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2587891104","https://openalex.org/W2590129515","https://openalex.org/W2745896134","https://openalex.org/W2796898542","https://openalex.org/W2799053639","https://openalex.org/W2926784911","https://openalex.org/W2936802426","https://openalex.org/W2948988029","https://openalex.org/W2950733131","https://openalex.org/W2963371159","https://openalex.org/W2963508548","https://openalex.org/W2963560054","https://openalex.org/W2964135678","https://openalex.org/W2964243274","https://openalex.org/W2967606780","https://openalex.org/W2972465261","https://openalex.org/W2972786657","https://openalex.org/W2981087920","https://openalex.org/W2989571531","https://openalex.org/W2990833974","https://openalex.org/W2999174651","https://openalex.org/W3007151378","https://openalex.org/W3013020904","https://openalex.org/W3024920698","https://openalex.org/W3026777299","https://openalex.org/W3039270522","https://openalex.org/W3104514529","https://openalex.org/W6685748340","https://openalex.org/W6760776128","https://openalex.org/W6770649806","https://openalex.org/W6777843394"],"related_works":["https://openalex.org/W2619026611","https://openalex.org/W2616987818","https://openalex.org/W2550171623","https://openalex.org/W2276250579","https://openalex.org/W596245619","https://openalex.org/W4389279190","https://openalex.org/W1875889864","https://openalex.org/W2164147372","https://openalex.org/W2279374969","https://openalex.org/W1990091944"],"abstract_inverted_index":{"Automatic":[0],"speaker":[1,22],"verification":[2,23],"(ASV)":[3],"systems":[4],"utilize":[5],"the":[6,14,34,46,81,92,122,130,138,142],"biometric":[7],"information":[8],"in":[9],"human":[10,95,126,143],"speech":[11,66,127,144,167],"to":[12,27,32,37,44,75,84],"verify":[13],"speaker's":[15],"identity.":[16],"The":[17],"techniques":[18,57],"used":[19],"for":[20,58,162],"performing":[21],"are":[24,159],"often":[25],"vulnerable":[26],"malicious":[28],"attacks":[29,100,102],"that":[30,120,132,149],"attempt":[31],"induce":[33],"ASV":[35,85,111],"system":[36,47],"return":[38],"wrong":[39],"results,":[40],"allowing":[41],"an":[42],"impostor":[43],"bypass":[45],"and":[48,109,156],"gain":[49],"access.":[50],"Attackers":[51],"use":[52],"a":[53],"multitude":[54],"of":[55,94,125,137,141,165],"spoofing":[56],"this,":[59],"such":[60],"as":[61],"voice":[62],"conversion,":[63],"audio":[64,78],"replay,":[65],"synthesis,":[67],"etc.":[68],"In":[69,87],"recent":[70],"years,":[71],"easily":[72],"available":[73],"tools":[74],"generate":[76],"deepfaked":[77,166],"have":[79],"increased":[80],"potential":[82,93],"threat":[83],"systems.":[86,112],"this":[88],"paper,":[89],"we":[90],"compare":[91],"impersonation":[96],"(voice":[97],"disguise)":[98],"based":[99,103],"with":[101],"on":[104,107],"machinegenerated":[105],"speech,":[106],"black-box":[108],"white-box":[110],"We":[113,147],"also":[114],"study":[115],"countermeasures":[116],"by":[117,169],"using":[118],"features":[119],"capture":[121],"unique":[123],"aspects":[124],"production,":[128],"under":[129],"hypothesis":[131],"machines":[133],"cannot":[134],"emulate":[135],"many":[136],"finelevel":[139],"intricacies":[140],"production":[145],"mechanism.":[146],"show":[148],"fundamental":[150],"frequency":[151],"sequence-related":[152],"entropy,":[153],"spectral":[154],"envelope,":[155],"aperiodic":[157],"parameters":[158],"promising":[160],"candidates":[161],"robust":[163],"detection":[164],"generated":[168],"unknown":[170],"methods.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
