{"id":"https://openalex.org/W4414804050","doi":"https://doi.org/10.1142/s0218194025500676","title":"Deepfake Audio Detection Using Generative Adversarial Network-Based Spatial\u2013Temporal Feature Learning","display_name":"Deepfake Audio Detection Using Generative Adversarial Network-Based Spatial\u2013Temporal Feature Learning","publication_year":2025,"publication_date":"2025-10-04","ids":{"openalex":"https://openalex.org/W4414804050","doi":"https://doi.org/10.1142/s0218194025500676"},"language":"en","primary_location":{"id":"doi:10.1142/s0218194025500676","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194025500676","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-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/A5108782617","display_name":"Vivek Ranjan","orcid":null},"institutions":[{"id":"https://openalex.org/I2799532815","display_name":"Madan Mohan Malaviya University of Technology","ror":"https://ror.org/04h1w2j35","country_code":"IN","type":"education","lineage":["https://openalex.org/I2799532815"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vivek Ranjan","raw_affiliation_strings":["Department of Information Technology and Computer Applications, Madan Mohan Malaviya University of Technology, Gorakhpur, Uttar Pradesh 273016, India"],"raw_orcid":"https://orcid.org/0009-0008-9574-7065","affiliations":[{"raw_affiliation_string":"Department of Information Technology and Computer Applications, Madan Mohan Malaviya University of Technology, Gorakhpur, Uttar Pradesh 273016, India","institution_ids":["https://openalex.org/I2799532815"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032117739","display_name":"Dayashankar Singh","orcid":"https://orcid.org/0009-0000-2212-1725"},"institutions":[{"id":"https://openalex.org/I2799532815","display_name":"Madan Mohan Malaviya University of Technology","ror":"https://ror.org/04h1w2j35","country_code":"IN","type":"education","lineage":["https://openalex.org/I2799532815"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dayashankar Singh","raw_affiliation_strings":["Department of Information Technology and Computer Applications, Madan Mohan Malaviya University of Technology, Gorakhpur, Uttar Pradesh 273016, India"],"raw_orcid":"https://orcid.org/0009-0000-2212-1725","affiliations":[{"raw_affiliation_string":"Department of Information Technology and Computer Applications, Madan Mohan Malaviya University of Technology, Gorakhpur, Uttar Pradesh 273016, India","institution_ids":["https://openalex.org/I2799532815"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2799532815"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2872931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"03","first_page":"363","last_page":"379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9763000011444092,"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":0.9763000011444092,"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":0.9714999794960022,"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":0.9643999934196472,"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/discriminator","display_name":"Discriminator","score":0.9115999937057495},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6675000190734863},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6017000079154968},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5710999965667725},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5633000135421753},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4230000078678131},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.3644999861717224},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3596000075340271},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3569999933242798}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9115999937057495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004000186920166},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6675000190734863},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6017000079154968},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5710999965667725},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5669000148773193},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5633000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400999784469604},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3716000020503998},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.3644999861717224},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.3278999924659729},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.30070000886917114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28540000319480896},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2696000039577484},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218194025500676","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194025500676","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W3119781965","https://openalex.org/W3126051646","https://openalex.org/W3160899975","https://openalex.org/W4223915588","https://openalex.org/W4381140704","https://openalex.org/W4387665604","https://openalex.org/W4388851105","https://openalex.org/W4389633690","https://openalex.org/W4389897623","https://openalex.org/W4390590496","https://openalex.org/W4393247956","https://openalex.org/W4394617057","https://openalex.org/W4396898756","https://openalex.org/W4398789263","https://openalex.org/W4399020875","https://openalex.org/W4400234286","https://openalex.org/W4400896787","https://openalex.org/W4401991736","https://openalex.org/W4403182579","https://openalex.org/W4403217519","https://openalex.org/W4404787858","https://openalex.org/W4405911176"],"related_works":[],"abstract_inverted_index":{"Deepfake":[0,20],"audio":[1,21,69,81],"detection":[2],"is":[3,22,82,135],"imperative":[4],"in":[5,42],"the":[6,43],"digital":[7],"era":[8],"as":[9],"it":[10],"has":[11,45],"a":[12,62,71,86,116,143,161],"detrimental":[13],"effect":[14],"on":[15,38,142],"individuals,":[16],"organizations":[17],"and":[18,25,32,89,93,106,160],"countries.":[19],"used":[23,47,136],"more":[24,26],"by":[27,115],"cybercriminals":[28],"for":[29,57,66,137],"impersonation,":[30],"fraud":[31],"voice":[33],"phishing,":[34],"necessitating":[35],"further":[36],"research":[37,41],"detection.":[39],"Previous":[40],"area":[44],"largely":[46],"supervised":[48,63],"learning,":[49],"which":[50],"provides":[51],"effective":[52],"results":[53,141],"using":[54,70,85],"labeled":[55],"data":[56],"training.":[58],"This":[59],"paper":[60],"proposes":[61],"learning":[64],"framework":[65],"detecting":[67],"deepfake":[68],"generative":[72],"adversarial":[73],"network":[74],"(GAN)":[75],"with":[76],"spatial\u2013temporal":[77,119],"feature":[78],"learning.":[79],"The":[80],"first":[83],"de-noised":[84],"Wiener":[87],"filter,":[88],"then":[90],"key":[91],"pitch":[92,101],"speech":[94,148],"features,":[95],"including":[96],"Mel-frequency":[97],"cepstral":[98],"coefficients":[99],"(MFCCs),":[100],"entropy,":[102],"harmonic-to-noise":[103],"ratio":[104],"(HNR)":[105],"glottal":[107],"flow,":[108],"are":[109,113],"extracted.":[110],"These":[111],"features":[112],"processed":[114],"one-dimensional":[117],"dilated":[118],"attention-based":[120],"bidirectional":[121],"gated":[122],"recurring":[123],"units":[124],"(ODDST-CBG)":[125],"to":[126],"capture":[127],"nuanced":[128],"patterns.":[129],"A":[130],"Wasserstein":[131],"GAN":[132],"(W-GAN)":[133],"discriminator":[134],"final":[138],"classification.":[139],"Experimental":[140],"large-scale":[144],"fake":[145],"versus":[146],"real":[147],"dataset":[149],"demonstrate":[150],"high":[151],"performance,":[152],"achieving":[153],"99.98%":[154],"accuracy,":[155],"99.08%":[156],"precision,":[157],"97.08%":[158,162],"sensitivity":[159],"F1-score,":[163],"surpassing":[164],"existing":[165],"baseline":[166],"methods.":[167]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}