{"id":"https://openalex.org/W4408345985","doi":"https://doi.org/10.1109/icassp49660.2025.10888175","title":"Fooling the Forgers: A Multi-Stage Framework for Audio Deepfake Detection","display_name":"Fooling the Forgers: A Multi-Stage Framework for Audio Deepfake Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345985","doi":"https://doi.org/10.1109/icassp49660.2025.10888175"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5076626481","display_name":"Gautam Siddharth Kashyap","orcid":"https://orcid.org/0000-0003-2140-9617"},"institutions":[{"id":"https://openalex.org/I19716509","display_name":"Jamia Hamdard","ror":"https://ror.org/03dwxvb85","country_code":"IN","type":"education","lineage":["https://openalex.org/I19716509"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Gautam Siddharth Kashyap","raw_affiliation_strings":["Jamia Hamdard,New Delhi,India"],"affiliations":[{"raw_affiliation_string":"Jamia Hamdard,New Delhi,India","institution_ids":["https://openalex.org/I19716509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114105249","display_name":"Zohaib Hasan Siddiqui","orcid":null},"institutions":[{"id":"https://openalex.org/I19716509","display_name":"Jamia Hamdard","ror":"https://ror.org/03dwxvb85","country_code":"IN","type":"education","lineage":["https://openalex.org/I19716509"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Zohaib Hasan Siddiqui","raw_affiliation_strings":["Jamia Hamdard,New Delhi,India"],"affiliations":[{"raw_affiliation_string":"Jamia Hamdard,New Delhi,India","institution_ids":["https://openalex.org/I19716509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093258760","display_name":"Mohammad Anas Azeez","orcid":"https://orcid.org/0009-0000-3344-0166"},"institutions":[{"id":"https://openalex.org/I19716509","display_name":"Jamia Hamdard","ror":"https://ror.org/03dwxvb85","country_code":"IN","type":"education","lineage":["https://openalex.org/I19716509"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mohammad Anas Azeez","raw_affiliation_strings":["Jamia Hamdard,New Delhi,India"],"affiliations":[{"raw_affiliation_string":"Jamia Hamdard,New Delhi,India","institution_ids":["https://openalex.org/I19716509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060535758","display_name":"Riyasat Ali","orcid":"https://orcid.org/0000-0003-4022-276X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafiq Ali","raw_affiliation_strings":["DSEU,New Delhi,India"],"affiliations":[{"raw_affiliation_string":"DSEU,New Delhi,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068965559","display_name":"Shantanu Kumar","orcid":"https://orcid.org/0009-0008-4459-8776"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shantanu Kumar","raw_affiliation_strings":["Amazon,Seattle,USA"],"affiliations":[{"raw_affiliation_string":"Amazon,Seattle,USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094363422","display_name":"Navin Kamuni","orcid":"https://orcid.org/0009-0001-8429-9788"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Navin Kamuni","raw_affiliation_strings":["Tech Mahindra Americas,Texas,USA"],"affiliations":[{"raw_affiliation_string":"Tech Mahindra Americas,Texas,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012051562","display_name":"Jiechao Gao","orcid":"https://orcid.org/0000-0003-0628-1416"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiechao Gao","raw_affiliation_strings":["University of Virginia,Virginia,USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia,Virginia,USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5076626481"],"corresponding_institution_ids":["https://openalex.org/I19716509"],"apc_list":null,"apc_paid":null,"fwci":5.4155,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95017558,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"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/T11309","display_name":"Music and Audio Processing","score":0.9894999861717224,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9894999861717224,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9567000269889832,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9279000163078308,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7541534900665283},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.49408772587776184},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4142535328865051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33192458748817444},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10302835702896118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541534900665283},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.49408772587776184},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4142535328865051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33192458748817444},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10302835702896118},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2296529392","https://openalex.org/W2533075636","https://openalex.org/W2889361425","https://openalex.org/W2972526452","https://openalex.org/W2972786657","https://openalex.org/W2972811785","https://openalex.org/W2973049979","https://openalex.org/W3026777299","https://openalex.org/W3160325739","https://openalex.org/W3191181235","https://openalex.org/W3206252155","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4287887329","https://openalex.org/W4297841787","https://openalex.org/W4317181815","https://openalex.org/W4367046815","https://openalex.org/W4401042610","https://openalex.org/W6776700526","https://openalex.org/W6783867762","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Audio":[0],"deepfakes":[1],"represent":[2],"a":[3,21,37,78],"risk":[4],"to":[5,50,99,114],"society":[6],"as":[7],"they":[8],"can":[9],"deteriorate":[10],"society\u2019s":[11],"trust":[12],"in":[13,36,83,117],"any":[14],"audio.":[15],"In":[16,41],"this":[17,110],"paper,":[18],"we":[19,44],"present":[20],"novel":[22],"approach":[23,90],"for":[24,68,94],"audio":[25,54],"deepfake":[26],"detection":[27,39,118],"using":[28],"Generative":[29],"Adversarial":[30],"Networks":[31],"(GANs)":[32],"and":[33,58,119],"contrastive":[34],"learning":[35,89],"multi-stage":[38],"framework.":[40],"our":[42],"process,":[43],"apply":[45],"the":[46,69,73,96],"Pre-trained":[47],"Models":[48],"(PTM)":[49],"extract":[51],"all":[52],"suitable":[53],"phonetics,":[55],"speaker":[56],"identity,":[57],"other":[59],"spatial":[60],"prosodic":[61],"features":[62],"or":[63],"contents,":[64],"which":[65],"are":[66],"crucial":[67],"model.":[70],"We":[71],"enhance":[72],"model\u2019s":[74,97],"performance":[75],"by":[76],"utilizing":[77],"GAN":[79],"data":[80],"augmentation":[81],"strategy":[82],"combination":[84],"with":[85],"HiFi-GAN.":[86],"The":[87],"Contrastive":[88],"is":[91,112],"then":[92],"used":[93],"improving":[95],"ability":[98],"discriminate":[100],"real":[101],"speech":[102],"from":[103],"fake":[104],"speech.":[105],"Our":[106],"experiments":[107],"demonstrate":[108],"that":[109],"method":[111],"superior":[113],"existing":[115],"methodologies":[116],"robustness.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-22T08:38:42.863108","created_date":"2025-10-10T00:00:00"}