{"id":"https://openalex.org/W4403331203","doi":"https://doi.org/10.1109/access.2024.3478731","title":"Hybrid Transformer Architectures With Diverse Audio Features for Deepfake Speech Classification","display_name":"Hybrid Transformer Architectures With Diverse Audio Features for Deepfake Speech Classification","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403331203","doi":"https://doi.org/10.1109/access.2024.3478731"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3478731","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3478731","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3478731","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015163401","display_name":"Khalid Zaman","orcid":"https://orcid.org/0009-0004-0809-7537"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Khalid Zaman","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109025228","display_name":"Islam J. A. M. Samiul","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Islam J. A. M. Samiul","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076533438","display_name":"Melike \u015eah","orcid":"https://orcid.org/0000-0003-3869-7205"},"institutions":[{"id":"https://openalex.org/I16197041","display_name":"Cyprus International University","ror":"https://ror.org/04mk5mk38","country_code":"CY","type":"education","lineage":["https://openalex.org/I16197041"]}],"countries":["CY"],"is_corresponding":false,"raw_author_name":"Melike Sah","raw_affiliation_strings":["Computer Engineering Department, Cyprus International University, North Cyprus, Nicosia, Türkiye"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Cyprus International University, North Cyprus, Nicosia, Türkiye","institution_ids":["https://openalex.org/I16197041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049336469","display_name":"Cem Direko\u011flu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cem Direkoglu","raw_affiliation_strings":["Electrical and Electronics Engineering Department, Middle East Technical University, Northern Cyprus Campus, Kalkanli, G\u00fczelyurt, Türkiye"],"affiliations":[{"raw_affiliation_string":"Electrical and Electronics Engineering Department, Middle East Technical University, Northern Cyprus Campus, Kalkanli, G\u00fczelyurt, Türkiye","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080920610","display_name":"Shogo Okada","orcid":"https://orcid.org/0000-0002-9260-0403"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shogo Okada","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5015163401"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":10.4804,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.98619686,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":null,"first_page":"149221","last_page":"149237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.989300012588501,"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":0.989300012588501,"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":0.988099992275238,"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":0.939300000667572,"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":0.7938442230224609},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5563638210296631},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.505805253982544},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4705432057380676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34124115109443665},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3301214575767517},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10537147521972656},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0749436616897583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7938442230224609},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5563638210296631},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.505805253982544},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4705432057380676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34124115109443665},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3301214575767517},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10537147521972656},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0749436616897583},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3478731","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3478731","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:57cd654c06664e49854ba892c36eb47b","is_oa":true,"landing_page_url":"https://doaj.org/article/57cd654c06664e49854ba892c36eb47b","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 149221-149237 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3478731","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3478731","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1837709900","https://openalex.org/W2562770010","https://openalex.org/W2737982026","https://openalex.org/W2936802426","https://openalex.org/W2967606780","https://openalex.org/W2972786657","https://openalex.org/W2973164265","https://openalex.org/W2973181078","https://openalex.org/W3004378172","https://openalex.org/W3007151378","https://openalex.org/W3015420010","https://openalex.org/W3026777299","https://openalex.org/W3039519447","https://openalex.org/W3048027105","https://openalex.org/W3085356816","https://openalex.org/W3096333737","https://openalex.org/W3101786243","https://openalex.org/W3128666957","https://openalex.org/W3131786367","https://openalex.org/W3135340083","https://openalex.org/W3154596443","https://openalex.org/W3158129762","https://openalex.org/W3180160903","https://openalex.org/W3205475937","https://openalex.org/W3206996142","https://openalex.org/W3212947338","https://openalex.org/W4214896311","https://openalex.org/W4221161255","https://openalex.org/W4226442948","https://openalex.org/W4282976775","https://openalex.org/W4286278015","https://openalex.org/W4309613630","https://openalex.org/W4312120855","https://openalex.org/W4312685284","https://openalex.org/W4360999163","https://openalex.org/W4372260443","https://openalex.org/W4372267124","https://openalex.org/W4385577110","https://openalex.org/W4386257516","https://openalex.org/W4386918931","https://openalex.org/W4388820942","https://openalex.org/W4390481409","https://openalex.org/W4390636217","https://openalex.org/W4392120540","https://openalex.org/W4392910532","https://openalex.org/W4392943326","https://openalex.org/W4399261702","https://openalex.org/W4400679783","https://openalex.org/W6793736971","https://openalex.org/W6794463088","https://openalex.org/W6797899870"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W1911859126","https://openalex.org/W3204019825","https://openalex.org/W2120730869","https://openalex.org/W1569721167","https://openalex.org/W2166699153","https://openalex.org/W2541680182"],"abstract_inverted_index":{"The":[0,144],"rise":[1],"of":[2,45,49,74,146,151,192,198,206,223,230],"synthetic":[3],"speech":[4,67,155],"technologies":[5],"has":[6],"triggered":[7],"growing":[8],"concerns":[9],"about":[10],"the":[11,39,43,50,71,157,171,177,208,215,236,244],"increasing":[12],"difficulty":[13],"in":[14],"distinguishing":[15],"between":[16],"real":[17,152],"and":[18,37,96,105,136,153,194,225,246],"fake":[19,66,154],"voices.":[20],"In":[21,77,118,204],"this":[22],"context,":[23],"we":[24,121],"propose":[25],"novel":[26],"hybrid":[27,57,85,162],"transformer-based":[28],"models":[29,59,81,164],"together":[30,60],"with":[31,61,84,107,149,161,176,184,214],"different":[32,62,113],"audio":[33,63,114,124,167],"feature":[34,115,173,210],"analysis":[35],"techniques":[36],"achieved":[38,239],"state-of-the-art":[40,182,247],"results.":[41],"To":[42],"best":[44,175,213],"our":[46,75,78,119,147],"knowledge,":[47],"none":[48],"existing":[51],"methods":[52],"have":[53],"considered":[54],"combining":[55],"various":[56,166],"transformer":[58,80,86,163],"features":[64,168],"for":[65],"classification,":[68],"which":[69],"forms":[70],"main":[72],"novelty":[73],"work.":[76],"work,":[79],"are":[82],"compared":[83,242],"architectures":[87],"including":[88],"Convolutional":[89],"Neural":[90],"Network":[91],"(CNN)-Transformer":[92],"(i.e.,":[93],"ResNet34-":[94],"Transformer":[95,106],"VGG16-Transformer":[97,216],"models),":[98],"Bi-directional":[99],"Long":[100],"Short-Term":[101],"Memory":[102],"(Bi-LSTM)-":[103],"Transformer,":[104],"Support":[108],"Vector":[109],"Machine":[110],"(SVM)":[111],"using":[112,156],"extraction":[116,126],"techniques.":[117],"approach,":[120],"utilize":[122],"three":[123],"attribute":[125],"techniques:":[127],"Mel":[128,131],"spectrogram":[129],"(Mel),":[130],"Frequency":[132],"Cepstral":[133],"Coefficient":[134],"(MFCC),":[135],"Short-Time":[137],"Fourier":[138],"Transform":[139],"(STFT)":[140],"as":[141],"input":[142],"representations.":[143],"results":[145,233],"evaluation":[148,195,227],"instances":[150],"ASVspoof":[158],"LA":[159],"dataset":[160],"across":[165],"indicate":[169,234],"that":[170,235],"STFT":[172,209],"performs":[174],"ResNet34-Transformer":[178],"model,":[179,217],"achieving":[180,218],"a":[181,185,219],"performance":[183,241],"development":[186,220],"set":[187,196,221,228],"equal":[188],"error":[189],"rate":[190],"(EER)":[191],"0.0%":[193],"EER":[197],"3.22%,":[199],"surpassing":[200],"all":[201],"other":[202],"methods.":[203,248],"terms":[205],"accuracy,":[207],"also":[211],"performed":[212],"accuracy":[222,229],"99.55%":[224],"an":[226],"94.04%.":[231],"These":[232],"proposed":[237],"study":[238],"better":[240],"to":[243],"baseline":[245]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":25}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}