{"id":"https://openalex.org/W4408353305","doi":"https://doi.org/10.1109/icassp49660.2025.10889022","title":"SpecViT: A Custom Vision-Transformer based Approach for Audio Deepfake Detection","display_name":"SpecViT: A Custom Vision-Transformer based Approach for Audio Deepfake Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353305","doi":"https://doi.org/10.1109/icassp49660.2025.10889022"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889022","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/A5030467646","display_name":"Subodh V. Modak","orcid":"https://orcid.org/0000-0001-9770-6576"},"institutions":[{"id":"https://openalex.org/I98365261","display_name":"Indian Institute of Engineering Science and Technology, Shibpur","ror":"https://ror.org/02ytfzr55","country_code":"IN","type":"education","lineage":["https://openalex.org/I98365261"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sharmistha Modak","raw_affiliation_strings":["Indian Institute of Engineering Science and Technology,Department of Information Technology,Shibpur,India,711103"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Engineering Science and Technology,Department of Information Technology,Shibpur,India,711103","institution_ids":["https://openalex.org/I98365261"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030398655","display_name":"Arnab Kumar Das","orcid":"https://orcid.org/0000-0003-3190-5817"},"institutions":[{"id":"https://openalex.org/I98365261","display_name":"Indian Institute of Engineering Science and Technology, Shibpur","ror":"https://ror.org/02ytfzr55","country_code":"IN","type":"education","lineage":["https://openalex.org/I98365261"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arnab Kumar Das","raw_affiliation_strings":["Indian Institute of Engineering Science and Technology,Department of Information Technology,Shibpur,India,711103"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Engineering Science and Technology,Department of Information Technology,Shibpur,India,711103","institution_ids":["https://openalex.org/I98365261"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031248267","display_name":"Ruchira Naskar","orcid":"https://orcid.org/0000-0001-6826-940X"},"institutions":[{"id":"https://openalex.org/I98365261","display_name":"Indian Institute of Engineering Science and Technology, Shibpur","ror":"https://ror.org/02ytfzr55","country_code":"IN","type":"education","lineage":["https://openalex.org/I98365261"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ruchira Naskar","raw_affiliation_strings":["Indian Institute of Engineering Science and Technology,Department of Information Technology,Shibpur,India,711103"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Engineering Science and Technology,Department of Information Technology,Shibpur,India,711103","institution_ids":["https://openalex.org/I98365261"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030467646"],"corresponding_institution_ids":["https://openalex.org/I98365261"],"apc_list":null,"apc_paid":null,"fwci":4.229,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93314884,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9810000061988831,"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"}},"topics":[{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9810000061988831,"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/T11309","display_name":"Music and Audio Processing","score":0.9610000252723694,"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":0.7173192501068115},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5794315338134766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38867220282554626},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36939507722854614},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32355958223342896},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16302698850631714},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.14052939414978027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7173192501068115},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5794315338134766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38867220282554626},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36939507722854614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32355958223342896},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16302698850631714},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.14052939414978027},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889022","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2003203713","https://openalex.org/W2295634712","https://openalex.org/W2558151185","https://openalex.org/W2885195348","https://openalex.org/W2888650348","https://openalex.org/W2963925437","https://openalex.org/W2999089077","https://openalex.org/W3005348841","https://openalex.org/W3017228721","https://openalex.org/W3019200173","https://openalex.org/W3026777299","https://openalex.org/W3033711348","https://openalex.org/W3036806226","https://openalex.org/W3084142230","https://openalex.org/W3140854437","https://openalex.org/W3146366485","https://openalex.org/W3152384838","https://openalex.org/W3161428216","https://openalex.org/W3186090001","https://openalex.org/W3197123936","https://openalex.org/W3200167423","https://openalex.org/W3204263825","https://openalex.org/W3212117663","https://openalex.org/W3212386989","https://openalex.org/W4214691743","https://openalex.org/W4221138880","https://openalex.org/W4224256913","https://openalex.org/W4225527248","https://openalex.org/W4226264925","https://openalex.org/W4288102863","https://openalex.org/W4298633873","https://openalex.org/W4320882980","https://openalex.org/W4381198892","https://openalex.org/W4382407365","https://openalex.org/W4385245566","https://openalex.org/W4385805162","https://openalex.org/W4385822347","https://openalex.org/W4386928847","https://openalex.org/W4388893647","https://openalex.org/W4390422207","https://openalex.org/W4391320804","https://openalex.org/W4392910532","https://openalex.org/W6763367864","https://openalex.org/W6769705151","https://openalex.org/W6784333009","https://openalex.org/W6797657831","https://openalex.org/W6799942944","https://openalex.org/W6872217232"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Degrees":[0],"of":[1,11,16,23,32,99],"hyper-realism":[2],"already":[3],"attained":[4],"by":[5,39,76],"present-day":[6],"deepfake":[7,61],"technology":[8],"poses":[9],"one":[10],"the":[12,33,43],"biggest":[13],"social":[14],"threats":[15,37],"today.":[17],"Deepfakes":[18],"may":[19],"involve":[20],"multiple":[21],"forms":[22],"media":[24],"including":[25],"audio,":[26],"video":[27],"and":[28,113],"images.":[29],"While":[30],"most":[31],"literature":[34],"deals":[35],"with":[36],"posed":[38],"visual":[40],"synthetic":[41,87],"media,":[42],"endeavor":[44],"to":[45],"uncover":[46],"audio":[47,60,72,100],"deepfakes":[48],"is":[49],"still":[50],"evolving;":[51],"it":[52],"demands":[53],"more":[54],"extensive":[55],"investigation.":[56],"Our":[57],"attempt":[58],"towards":[59],"detection":[62],"in":[63,71],"this":[64],"article,":[65],"involves":[66],"investigating":[67],"spectral":[68],"patterns":[69],"present":[70],"spectrograms,":[73],"captured":[74],"appropriately":[75],"a":[77],"two-attention":[78],"vision":[79],"transformer":[80],"model":[81,95],"(SpecViT2A),":[82],"finally":[83],"exploited":[84],"for":[85,96],"discriminating":[86],"audios":[88],"from":[89],"pristine":[90],"ones.":[91],"We":[92],"employed":[93],"our":[94],"successful":[97],"identification":[98],"as":[101,103,115,117],"well":[102],"multimodal":[104],"deepfakes,":[105],"yielding":[106],"best":[107],"accuracy":[108],"over":[109],"99%,":[110],"F1-score":[111],"0.9911,":[112],"EER":[114],"low":[116],"3.5":[118],"on":[119],"ASVSpoof":[120],"2021.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}