{"id":"https://openalex.org/W4416208967","doi":"https://doi.org/10.3390/a18110716","title":"AudioFakeNet: A Model for Reliable Speaker Verification in Deepfake Audio","display_name":"AudioFakeNet: A Model for Reliable Speaker Verification in Deepfake Audio","publication_year":2025,"publication_date":"2025-11-13","ids":{"openalex":"https://openalex.org/W4416208967","doi":"https://doi.org/10.3390/a18110716"},"language":"en","primary_location":{"id":"doi:10.3390/a18110716","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18110716","pdf_url":"https://www.mdpi.com/1999-4893/18/11/716/pdf?version=1763030023","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/18/11/716/pdf?version=1763030023","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059052729","display_name":"Samia Dilbar","orcid":"https://orcid.org/0000-0002-3526-1601"},"institutions":[{"id":"https://openalex.org/I174731842","display_name":"Islamia University of Bahawalpur","ror":"https://ror.org/002rc4w13","country_code":"PK","type":"education","lineage":["https://openalex.org/I174731842"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Samia Dilbar","raw_affiliation_strings":["Department of Electrical Engineering, Islamia University of Bahawalpur, Bahawalpur 63100, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Islamia University of Bahawalpur, Bahawalpur 63100, Pakistan","institution_ids":["https://openalex.org/I174731842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040747484","display_name":"Muhammad Ali Qureshi","orcid":"https://orcid.org/0000-0003-4390-2461"},"institutions":[{"id":"https://openalex.org/I174731842","display_name":"Islamia University of Bahawalpur","ror":"https://ror.org/002rc4w13","country_code":"PK","type":"education","lineage":["https://openalex.org/I174731842"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Ali Qureshi","raw_affiliation_strings":["Department of Information and Communication Engineering, Islamia University of Bahawalpur, Bahawalpur 63100, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, Islamia University of Bahawalpur, Bahawalpur 63100, Pakistan","institution_ids":["https://openalex.org/I174731842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025814708","display_name":"Serosh Karim Noon","orcid":"https://orcid.org/0000-0002-8760-0628"},"institutions":[{"id":"https://openalex.org/I4403386657","display_name":"NFC Institute of Engineering and Technology","ror":"https://ror.org/00vzebw12","country_code":null,"type":"education","lineage":["https://openalex.org/I4403386636","https://openalex.org/I4403386657"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Serosh Karim Noon","raw_affiliation_strings":["Department of Electrical Engineering, NFC Institute of Engineering & Technology, Multan 60000, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, NFC Institute of Engineering & Technology, Multan 60000, Pakistan","institution_ids":["https://openalex.org/I4403386657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081140948","display_name":"Abdul Mannan","orcid":"https://orcid.org/0000-0001-9964-2633"},"institutions":[{"id":"https://openalex.org/I4210114955","display_name":"Muhammad Nawaz Sharif University of Engineering & Technology","ror":"https://ror.org/023e9bm81","country_code":"PK","type":"education","lineage":["https://openalex.org/I4210114955"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Abdul Mannan","raw_affiliation_strings":["Department of Biomedical Engineering, NFC Institute of Engineering & Technology, Multan 60000, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, NFC Institute of Engineering & Technology, Multan 60000, Pakistan","institution_ids":["https://openalex.org/I4210114955"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025814708","https://openalex.org/A5059052729"],"corresponding_institution_ids":["https://openalex.org/I174731842","https://openalex.org/I4403386657"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18950228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"11","first_page":"716","last_page":"716"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6011999845504761,"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":0.6011999845504761,"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":0.06960000097751617,"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":0.05339999869465828,"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/deep-learning","display_name":"Deep learning","score":0.6628999710083008},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5917999744415283},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5831000208854675},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5372999906539917},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5277000069618225},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.5149000287055969},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5002999901771545},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47600001096725464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8863000273704529},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6628999710083008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6216999888420105},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5533999800682068},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5372999906539917},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5002999901771545},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.42500001192092896},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37860000133514404},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.36250001192092896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/a18110716","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18110716","pdf_url":"https://www.mdpi.com/1999-4893/18/11/716/pdf?version=1763030023","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:456d0ff7dfc543a982de02ec8ad0098a","is_oa":true,"landing_page_url":"https://doaj.org/article/456d0ff7dfc543a982de02ec8ad0098a","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":"Algorithms, Vol 18, Iss 11, p 716 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a18110716","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18110716","pdf_url":"https://www.mdpi.com/1999-4893/18/11/716/pdf?version=1763030023","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416208967.pdf","grobid_xml":"https://content.openalex.org/works/W4416208967.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2967104857","https://openalex.org/W2972811785","https://openalex.org/W3135508679","https://openalex.org/W3173222908","https://openalex.org/W4308982542","https://openalex.org/W4312743281","https://openalex.org/W4317734114","https://openalex.org/W4380990703","https://openalex.org/W4385800847","https://openalex.org/W4386389284","https://openalex.org/W4387665604","https://openalex.org/W4388740187","https://openalex.org/W4393185179","https://openalex.org/W4394617057","https://openalex.org/W4396785992","https://openalex.org/W4399556751","https://openalex.org/W4400234286","https://openalex.org/W4400615608","https://openalex.org/W4400678935","https://openalex.org/W4400905960","https://openalex.org/W4401208497","https://openalex.org/W4402220980","https://openalex.org/W4403054584","https://openalex.org/W4403331203","https://openalex.org/W4403955261","https://openalex.org/W4406356474","https://openalex.org/W4406692008","https://openalex.org/W4406812016","https://openalex.org/W4406821510","https://openalex.org/W4407172089","https://openalex.org/W4407785391","https://openalex.org/W4409375459","https://openalex.org/W4410492041","https://openalex.org/W4410748035","https://openalex.org/W4410842662"],"related_works":[],"abstract_inverted_index":{"Deepfake":[0],"audio":[1,98],"refers":[2],"to":[3,94],"the":[4,49,110],"generation":[5],"of":[6,31],"voice":[7],"recordings":[8],"using":[9,104],"deep":[10,56,129],"neural":[11],"networks":[12],"that":[13,59,133],"replicate":[14],"a":[15,54],"specific":[16],"individual\u2019s":[17],"voice,":[18],"often":[19],"for":[20,33,42,77,152],"deceptive":[21],"or":[22],"fraud":[23],"purposes.":[24],"Although":[25],"this":[26],"has":[27],"been":[28],"an":[29],"area":[30],"research":[32],"quite":[34],"some":[35],"time,":[36],"deepfakes":[37],"still":[38],"pose":[39],"substantial":[40],"challenges":[41],"reliable":[43],"true":[44],"speaker":[45],"authentication.":[46],"To":[47],"address":[48],"issue,":[50],"we":[51],"propose":[52],"AudioFakeNet,":[53],"hybrid":[55],"learning":[57,127,130],"architecture":[58],"use":[60],"Convolutional":[61],"Neural":[62],"Networks":[63],"(CNNs)":[64],"along":[65],"with":[66,124],"Long":[67],"Short-Term":[68],"Memory":[69],"(LSTM)":[70],"units,":[71],"and":[72,84,91,114,128,142],"Multi-Head":[73],"Attention":[74],"(MHA)":[75],"mechanisms":[76],"robust":[78],"deepfake":[79],"detection.":[80],"CNN":[81],"extracts":[82],"spatial":[83],"spectral":[85],"features,":[86],"LSTM":[87],"captures":[88],"temporal":[89],"dependencies,":[90],"MHA":[92],"enhances":[93],"focus":[95],"on":[96,117],"informative":[97],"segments.":[99],"The":[100],"model":[101],"is":[102],"trained":[103],"Mel-Frequency":[105],"Cepstral":[106],"Coefficients":[107],"(MFCCs)":[108],"from":[109],"publicly":[111],"available":[112],"dataset":[113],"was":[115],"validated":[116],"self-collected":[118],"dataset,":[119],"ensuring":[120],"reproducibility.":[121],"Performance":[122],"comparisons":[123],"state-of-the-art":[125],"machine":[126],"models":[131],"show":[132],"our":[134],"proposed":[135],"AudioFakeNet":[136],"achieves":[137],"higher":[138],"accuracy,":[139],"better":[140],"generalization,":[141],"lower":[143],"Equal":[144],"Error":[145],"Rate":[146],"(EER).":[147],"Its":[148],"modular":[149],"design":[150],"allows":[151],"broader":[153],"adaptability":[154],"in":[155],"fake-audio":[156],"detection":[157],"tasks,":[158],"offering":[159],"significant":[160],"potential":[161],"across":[162],"diverse":[163],"speech":[164],"synthesis":[165],"applications.":[166]},"counts_by_year":[],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-11-14T00:00:00"}