{"id":"https://openalex.org/W4392902701","doi":"https://doi.org/10.1109/icassp48485.2024.10447500","title":"Frame-to-Utterance Convergence: A Spectra-Temporal Approach for Unified Spoofing Detection","display_name":"Frame-to-Utterance Convergence: A Spectra-Temporal Approach for Unified Spoofing Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902701","doi":"https://doi.org/10.1109/icassp48485.2024.10447500"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5085960321","display_name":"Awais Khan","orcid":"https://orcid.org/0000-0003-2603-3516"},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Awais Khan","raw_affiliation_strings":["Oakland University,Department of Computer Science and Engineering,Rochester,Michigan,USA","Department of Computer Science and Engineering, Oakland University, Rochester, Michigan, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oakland University,Department of Computer Science and Engineering,Rochester,Michigan,USA","institution_ids":["https://openalex.org/I177721651"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Oakland University, Rochester, Michigan, USA","institution_ids":["https://openalex.org/I177721651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024102795","display_name":"Khalid Mahmood Malik","orcid":"https://orcid.org/0000-0002-7927-3436"},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]},{"id":"https://openalex.org/I4210092198","display_name":"University of Michigan\u2013Flint","ror":"https://ror.org/01c3xc117","country_code":"US","type":"education","lineage":["https://openalex.org/I4210092198"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khalid Mahmood Malik","raw_affiliation_strings":["Oakland University,Department of Computer Science and Engineering,Rochester,Michigan,USA","Department of Computer Science and Engineering, Oakland University, Rochester, Michigan, USA","College of Innovation and Technology, University of Michigan-Flint, Michigan, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oakland University,Department of Computer Science and Engineering,Rochester,Michigan,USA","institution_ids":["https://openalex.org/I177721651"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Oakland University, Rochester, Michigan, USA","institution_ids":["https://openalex.org/I177721651"]},{"raw_affiliation_string":"College of Innovation and Technology, University of Michigan-Flint, Michigan, USA","institution_ids":["https://openalex.org/I4210092198"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016485532","display_name":"Shah Nawaz","orcid":"https://orcid.org/0000-0002-7715-4409"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Shah Nawaz","raw_affiliation_strings":["Johannes Kepler University,Linz,Austria","Johannes Kepler University, Linz, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johannes Kepler University,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0547,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.9205847,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10761","last_page":"10765"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10863","display_name":"Voice and Speech Disorders","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9940000176429749,"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":0.9091153740882874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.802986741065979},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7177599668502808},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6031913161277771},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5914045572280884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5011453628540039},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.42303457856178284},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41559866070747375},{"id":"https://openalex.org/keywords/liveness","display_name":"Liveness","score":0.41465091705322266},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35681015253067017},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.16753551363945007},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.12006592750549316},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11370870471000671},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07314497232437134}],"concepts":[{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.9091153740882874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802986741065979},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7177599668502808},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6031913161277771},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5914045572280884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011453628540039},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42303457856178284},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41559866070747375},{"id":"https://openalex.org/C15569618","wikidata":"https://www.wikidata.org/wiki/Q3561421","display_name":"Liveness","level":2,"score":0.41465091705322266},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35681015253067017},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.16753551363945007},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.12006592750549316},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11370870471000671},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07314497232437134},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2951639392","https://openalex.org/W2972811785","https://openalex.org/W3013020904","https://openalex.org/W3017138616","https://openalex.org/W3024869864","https://openalex.org/W3043119861","https://openalex.org/W3090254849","https://openalex.org/W3161011913","https://openalex.org/W3197457172","https://openalex.org/W3198329097","https://openalex.org/W3199131409","https://openalex.org/W3199161700","https://openalex.org/W3200167423","https://openalex.org/W3200876013","https://openalex.org/W3201397251","https://openalex.org/W3212117663","https://openalex.org/W4225527248","https://openalex.org/W4382371735","https://openalex.org/W4385999783","https://openalex.org/W4390523451","https://openalex.org/W6783527727"],"related_works":["https://openalex.org/W2533239677","https://openalex.org/W4389545061","https://openalex.org/W2140593870","https://openalex.org/W3126377002","https://openalex.org/W2903861076","https://openalex.org/W2604576816","https://openalex.org/W2729608596","https://openalex.org/W2913345013","https://openalex.org/W2900020547","https://openalex.org/W3016508785"],"abstract_inverted_index":{"Voice":[0],"spoofing":[1,51,56,61,135],"attacks":[2],"pose":[3],"a":[4,42,78,88,100,161],"significant":[5],"threat":[6],"to":[7,49,71,127],"automated":[8],"speaker":[9],"verification":[10],"systems.":[11],"Existing":[12],"anti-spoofing":[13],"methods":[14],"often":[15],"simulate":[16],"specific":[17],"attack":[18],"types,":[19],"such":[20],"as":[21],"synthetic":[22],"or":[23,65],"replay":[24],"attacks.":[25,143],"However,":[26],"in":[27],"real-world":[28],"scenarios,":[29],"the":[30,35,39,60],"countermeasures":[31],"are":[32,69],"unaware":[33],"of":[34,38,164],"generation":[36],"schema":[37],"attack,":[40],"necessitating":[41],"unified":[43,46],"solution.":[44],"Current":[45],"solutions":[47],"struggle":[48],"detect":[50],"artefacts,":[52],"especially":[53],"with":[54],"recent":[55],"mechanisms.":[57],"For":[58],"instance,":[59],"algorithms":[62],"inject":[63],"spectral":[64,91],"temporal":[66,105],"anomalies,":[67],"which":[68,108],"challenging":[70],"identify.":[72],"To":[73],"this":[74],"end,":[75],"we":[76],"present":[77],"spectra-temporal":[79,113,123],"fusion":[80,114],"leveraging":[81],"frame-level":[82,96],"and":[83,98,119,140,154],"utterance-level":[84,110],"coefficients.":[85],"We":[86],"introduce":[87],"novel":[89],"local":[90],"deviation":[92],"coefficient":[93],"(SDC)":[94],"for":[95,103,160],"inconsistencies":[97],"employ":[99],"bi-LSTM-based":[101],"network":[102],"sequential":[104],"coefficients":[106,125],"(STC),":[107],"capture":[109],"artifacts.":[111],"Our":[112,130],"strategy":[115],"combines":[116],"these":[117],"coefficients,":[118],"an":[120],"auto-encoder":[121],"generates":[122],"deviated":[124],"(STDC)":[126],"enhance":[128],"robustness.":[129],"proposed":[131],"approach":[132],"addresses":[133],"multiple":[134],"categories,":[136],"including":[137],"synthetic,":[138],"replay,":[139],"partial":[141,152],"deepfake":[142],"Extensive":[144],"evaluation":[145],"on":[146],"diverse":[147],"datasets":[148],"(ASVspoof2019,":[149],"ASVspoof2021,":[150],"VSDC,":[151],"spoofs,":[153],"in-the-wild":[155],"deepfakes)":[156],"demonstrated":[157],"its":[158],"robustness":[159],"wide":[162],"range":[163],"voice":[165],"applications.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}