{"id":"https://openalex.org/W4416252253","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229195","title":"Robust Deepfake Speech Algorithm Recognition: Classifying Generative Algorithms via Speaker X-Vectors and Deep Learning","display_name":"Robust Deepfake Speech Algorithm Recognition: Classifying Generative Algorithms via Speaker X-Vectors and Deep Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252253","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229195"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5044013857","display_name":"Harry Maltby","orcid":"https://orcid.org/0000-0003-0142-6575"},"institutions":[{"id":"https://openalex.org/I157227730","display_name":"University of East London","ror":"https://ror.org/057jrqr44","country_code":"GB","type":"education","lineage":["https://openalex.org/I157227730"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Harry Maltby","raw_affiliation_strings":["University of East London,School of Architecture, Computing and Engineering,London,UK"],"affiliations":[{"raw_affiliation_string":"University of East London,School of Architecture, Computing and Engineering,London,UK","institution_ids":["https://openalex.org/I157227730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063632288","display_name":"Julie Wall","orcid":"https://orcid.org/0000-0001-6714-4867"},"institutions":[{"id":"https://openalex.org/I177463362","display_name":"University of West London","ror":"https://ror.org/03e5mzp60","country_code":"GB","type":"education","lineage":["https://openalex.org/I177463362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Julie Wall","raw_affiliation_strings":["University of West London,School of Computing and Engineering,London,UK"],"affiliations":[{"raw_affiliation_string":"University of West London,School of Computing and Engineering,London,UK","institution_ids":["https://openalex.org/I177463362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044554092","display_name":"Cornelius Glackin","orcid":"https://orcid.org/0000-0001-5114-6403"},"institutions":[{"id":"https://openalex.org/I4210138417","display_name":"Verint Systems (United States)","ror":"https://ror.org/03fqhrc68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138417"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cornelius Glackin","raw_affiliation_strings":["Verint Systems UK Ltd.,London,UK"],"affiliations":[{"raw_affiliation_string":"Verint Systems UK Ltd.,London,UK","institution_ids":["https://openalex.org/I4210138417"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087019252","display_name":"M. Moniri","orcid":"https://orcid.org/0000-0002-5564-0692"},"institutions":[{"id":"https://openalex.org/I157227730","display_name":"University of East London","ror":"https://ror.org/057jrqr44","country_code":"GB","type":"education","lineage":["https://openalex.org/I157227730"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mansour Moniri","raw_affiliation_strings":["University of East London,School of Architecture, Computing and Engineering,London,UK"],"affiliations":[{"raw_affiliation_string":"University of East London,School of Architecture, Computing and Engineering,London,UK","institution_ids":["https://openalex.org/I157227730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021596654","display_name":"Roman Shrestha","orcid":"https://orcid.org/0000-0002-7420-1329"},"institutions":[{"id":"https://openalex.org/I4210138417","display_name":"Verint Systems (United States)","ror":"https://ror.org/03fqhrc68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138417"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roman Shrestha","raw_affiliation_strings":["Verint Systems UK Ltd.,London,UK"],"affiliations":[{"raw_affiliation_string":"Verint Systems UK Ltd.,London,UK","institution_ids":["https://openalex.org/I4210138417"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012466886","display_name":"Nigel Cannings","orcid":"https://orcid.org/0000-0002-5279-3968"},"institutions":[{"id":"https://openalex.org/I4210138417","display_name":"Verint Systems (United States)","ror":"https://ror.org/03fqhrc68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138417"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nigel Cannings","raw_affiliation_strings":["Verint Systems UK Ltd.,London,UK"],"affiliations":[{"raw_affiliation_string":"Verint Systems UK Ltd.,London,UK","institution_ids":["https://openalex.org/I4210138417"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086212451","display_name":"Iwa Salami","orcid":"https://orcid.org/0000-0003-4864-5863"},"institutions":[{"id":"https://openalex.org/I157227730","display_name":"University of East London","ror":"https://ror.org/057jrqr44","country_code":"GB","type":"education","lineage":["https://openalex.org/I157227730"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iwa Salami","raw_affiliation_strings":["University of East London,Royal Docks School of Business and Law,London,UK"],"affiliations":[{"raw_affiliation_string":"University of East London,Royal Docks School of Business and Law,London,UK","institution_ids":["https://openalex.org/I157227730"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5044013857"],"corresponding_institution_ids":["https://openalex.org/I157227730"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19520675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.41339999437332153,"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":0.41339999437332153,"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":0.14180000126361847,"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":0.0729999989271164,"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/robustness","display_name":"Robustness (evolution)","score":0.6855999827384949},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.46160000562667847},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41530001163482666},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.40450000762939453},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.40130001306533813},{"id":"https://openalex.org/keywords/decision-boundary","display_name":"Decision boundary","score":0.3790000081062317},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3723999857902527},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.3723999857902527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8030999898910522},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6855999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6098999977111816},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47909998893737793},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4156999886035919},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.3790000081062317},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3723999857902527},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.36559998989105225},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.33489999175071716},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C78397625","wikidata":"https://www.wikidata.org/wiki/Q192487","display_name":"Discriminant","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30979999899864197},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":18,"referenced_works":["https://openalex.org/W2696967604","https://openalex.org/W2890964092","https://openalex.org/W2992308087","https://openalex.org/W3015598461","https://openalex.org/W3020336359","https://openalex.org/W3038871978","https://openalex.org/W3196595845","https://openalex.org/W3199131409","https://openalex.org/W3207579445","https://openalex.org/W4206908380","https://openalex.org/W4224925136","https://openalex.org/W4298394324","https://openalex.org/W4301373694","https://openalex.org/W4312326706","https://openalex.org/W4381198892","https://openalex.org/W4391266552","https://openalex.org/W4398186462","https://openalex.org/W4402353810"],"related_works":[],"abstract_inverted_index":{"The":[0,39],"rapid":[1],"advancement":[2],"of":[3,12,195,238,324],"deepfake":[4,45,86,126,325],"voice":[5,94,173,304],"technologies":[6],"has":[7],"resulted":[8],"in":[9,184,321],"alarming":[10],"cases":[11,84],"impersonation":[13],"and":[14,61,66,72,82,139,144,155,166,224,231,247,254,272,318],"deception,":[15],"highlighting":[16],"the":[17,35,50,75,98,179,185,199,236,277,285,322],"urgent":[18],"need":[19],"for":[20,56,125,162,228,303,314],"robust":[21,65,317],"tools":[22,76],"that":[23,190],"can":[24],"not":[25,42],"only":[26,43],"distinguish":[27],"real":[28],"audio":[29,46,142],"from":[30,100,260],"fake":[31],"but":[32,47],"also":[33,48],"recognise":[34,49],"generative":[36,51],"algorithms":[37],"responsible.":[38],"ability":[40],"to":[41,78,105,116,178,221,262,306],"detect":[44],"methods":[52,181],"used":[53,183],"is":[54,103,109],"essential":[55],"forensic":[57],"investigations,":[58],"legal":[59,70],"proceedings,":[60],"regulatory":[62],"enforcement.":[63],"Without":[64],"explainable":[67],"detection":[68],"frameworks,":[69],"professionals":[71],"investigators":[73],"lack":[74],"needed":[77],"effectively":[79],"monitor,":[80],"investigate,":[81],"prosecute":[83],"involving":[85],"misuse.":[87],"In":[88],"this":[89],"work,":[90],"we":[91,234],"take":[92],"a":[93,133,163,209,264,273,299,312],"biometrics":[95],"approach,":[96],"shifting":[97],"focus":[99],"identifying":[101,106],"who":[102],"speaking":[104],"which":[107,197],"algorithm":[108,128],"speaking.":[110],"Doing":[111],"so":[112],"allows":[113,161],"our":[114,145,202,214,248,257,268],"approach":[115,160],"inherently":[117],"handle":[118],"unseen":[119],"classes":[120],"while":[121,207],"achieving":[122],"competitive":[123],"performance":[124],"speech":[127,326],"recognition.":[129],"Our":[130],"system":[131,252,286],"leverages":[132],"voice-focused":[134],"ResNet101-based":[135],"x-vector":[136],"extraction":[137],"model":[138,215],"combines":[140],"diverse":[141],"features,":[143],"experimental":[146],"novel":[147,249],"feature":[148,245],"LFCC-HF,":[149],"enhanced":[150],"with":[151,213,244],"Linear":[152],"Discriminant":[153],"Analysis":[154],"cosine":[156],"similarity":[157,174,305],"clustering.":[158],"This":[159,309],"more":[164,316],"transparent":[165],"interpretable":[167,319],"decision-making":[168,200],"process":[169],"by":[170],"usinga":[171],"single":[172,270],"decision":[175],"boundary":[176],"compared":[177,220],"ensemble-based":[180],"commonly":[182],"literature.":[186],"Unlike":[187],"previous":[188],"works":[189],"rely":[191],"on":[192,298],"an":[193],"ensemble":[194],"models,":[196],"convolute":[198],"process,":[201,293],"method":[203],"achieves":[204,287],"comparable":[205],"results":[206],"using":[208],"significantly":[210],"lighter-weight":[211],"architecture,":[212],"having":[216],"14.84":[217],"M":[218,223,226],"parameters":[219,227],"95":[222],"317":[225],"Wav2Vec2":[229],"base":[230],"large.":[232],"Furthermore,":[233],"demonstrate":[235],"benefits":[237],"targeted":[239],"data":[240],"augmentation,":[241],"which,":[242],"combined":[243],"fusion":[246],"feature,":[250,271],"improves":[251],"robustness":[253],"adaptability,":[255],"increasing":[256],"F1":[258],"Score":[259],"0.624":[261],"0.763,":[263],"22.275%":[265],"increase":[266,275],"over":[267,276],"best":[269,278],"40.775%":[274],"ADD":[279],"2023":[280],"Track":[281],"3":[282],"baseline.":[283],"Importantly,":[284],"interpretability":[288],"through":[289],"its":[290],"back-end":[291],"classification":[292],"where":[294],"decisions":[295],"are":[296],"based":[297],"transparent,":[300],"learned":[301],"threshold":[302],"known":[307],"voiceprints.":[308],"work":[310],"offers":[311],"foundation":[313],"advancing":[315],"solutions":[320],"field":[323],"detection.":[327]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}