{"id":"https://openalex.org/W3024758142","doi":"https://doi.org/10.21437/odyssey.2020-47","title":"An Explainability Study of the Constant Q Cepstral Coefficient Spoofing Countermeasure for Automatic Speaker Verification","display_name":"An Explainability Study of the Constant Q Cepstral Coefficient Spoofing Countermeasure for Automatic Speaker Verification","publication_year":2020,"publication_date":"2020-05-15","ids":{"openalex":"https://openalex.org/W3024758142","doi":"https://doi.org/10.21437/odyssey.2020-47","mag":"3024758142"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2020-47","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-47","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","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/A5018712252","display_name":"Hemlata Tak","orcid":"https://orcid.org/0000-0002-0102-523X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hemlata Tak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046246613","display_name":"Jos\u00e9 Patino","orcid":"https://orcid.org/0000-0001-7193-0721"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jose Patino","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019383045","display_name":"Andreas Nautsch","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Nautsch","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066811192","display_name":"Nicholas Evans","orcid":"https://orcid.org/0000-0002-8459-1041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicholas Evans","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049594655","display_name":"Massimiliano Todisco","orcid":"https://orcid.org/0000-0003-2883-0324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Massimiliano Todisco","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018712252"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1814,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.93186687,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"333","last_page":"340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9894000291824341,"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":0.7352506518363953},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6659176349639893},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6627506017684937},{"id":"https://openalex.org/keywords/countermeasure","display_name":"Countermeasure","score":0.6396712064743042},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.5930512547492981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5169252753257751},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46494096517562866},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4496331214904785},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.29907822608947754},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2469087541103363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17929399013519287},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12211385369300842},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.09708565473556519}],"concepts":[{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.7352506518363953},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6659176349639893},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6627506017684937},{"id":"https://openalex.org/C21593369","wikidata":"https://www.wikidata.org/wiki/Q1032176","display_name":"Countermeasure","level":2,"score":0.6396712064743042},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5930512547492981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5169252753257751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46494096517562866},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4496331214904785},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.29907822608947754},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2469087541103363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17929399013519287},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12211385369300842},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.09708565473556519},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/odyssey.2020-47","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-47","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2954943288","https://openalex.org/W2303197844","https://openalex.org/W2156831951","https://openalex.org/W4301934879","https://openalex.org/W2765358162","https://openalex.org/W2548694291","https://openalex.org/W2073854657","https://openalex.org/W3173366380","https://openalex.org/W2836844603","https://openalex.org/W2726823740"],"abstract_inverted_index":{"Anti-spoofing":[0],"for":[1],"automatic":[2],"speaker":[3],"verification":[4],"is":[5,128],"now":[6],"a":[7,71,192],"well":[8],"established":[9],"area":[10],"of":[11,28,40,88,111,135,145,183,195],"research,":[12],"with":[13,70],"three":[14],"competitive":[15],"challenges":[16],"having":[17],"been":[18,35,60,153],"held":[19],"in":[20,66,84,105,132],"the":[21,38,45,106,112,133,146],"last":[22],"6":[23],"years.":[24],"A":[25],"great":[26],"deal":[27],"research":[29],"effort":[30],"over":[31],"this":[32],"time":[33],"has":[34,152],"invested":[36],"into":[37],"development":[39],"front-end":[41,94,140],"representations":[42,95],"tailored":[43],"to":[44,62,121,130,141,168,179,203],"spoofing":[46,89,162,184],"detection":[47],"task.":[48],"One":[49],"such":[50],"approach":[51],"known":[52],"as":[53],"constant":[54],"Q":[55],"cepstral":[56],"coefficients":[57],"(CQCCs)":[58],"have":[59],"shown":[61,129],"be":[63,200],"especially":[64],"effective":[65],"detecting":[67,85],"attacks":[68],"implemented":[69],"unit":[72],"selection":[73],"based":[74],"speech":[75],"synthesis":[76],"algorithm.":[77],"Despite":[78],"their":[79],"success,":[80],"they":[81],"largely":[82],"fail":[83],"other":[86],"forms":[87,182],"attack":[90,185],"where":[91],"more":[92,205],"traditional":[93],"give":[96],"substantially":[97],"better":[98,193,201],"results.":[99],"Similar":[100],"differences":[101],"were":[102],"also":[103],"observed":[104],"most":[107],"recent,":[108],"2019":[109],"edition":[110],"ASVspoof":[113],"challenge":[114],"series.":[115],"This":[116],"paper":[117],"reports":[118],"our":[119],"attempts":[120],"help":[122],"explain":[123],"these":[124,196],"observations.":[125],"The":[126],"explanation":[127],"lie":[131],"level":[134,175],"attention":[136],"paid":[137],"by":[138,161],"each":[139],"different":[142,181],"sub-band":[143],"components":[144],"spectrum.":[147],"Thus":[148],"far,":[149],"surprisingly":[150],"little":[151],"learned":[154],"about":[155],"what":[156],"artefacts":[157,176,197],"are":[158],"being":[159],"detected":[160],"countermeasures.":[163,207],"Our":[164],"work":[165],"hence":[166],"aims":[167],"shed":[169],"light":[170],"upon":[171],"signal":[172],"or":[173],"spectrum":[174],"that":[177],"serve":[178],"distinguish":[180],"from":[186],"genuine,":[187],"bone":[188],"fide":[189],"speech.":[190],"With":[191],"understanding":[194],"we":[198],"will":[199],"positioned":[202],"design":[204],"reliable":[206]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}