{"id":"https://openalex.org/W4399556751","doi":"https://doi.org/10.1145/3658664.3659647","title":"Detecting Audio Deepfakes: Integrating CNN and BiLSTM with Multi-Feature Concatenation","display_name":"Detecting Audio Deepfakes: Integrating CNN and BiLSTM with Multi-Feature Concatenation","publication_year":2024,"publication_date":"2024-06-12","ids":{"openalex":"https://openalex.org/W4399556751","doi":"https://doi.org/10.1145/3658664.3659647"},"language":"en","primary_location":{"id":"doi:10.1145/3658664.3659647","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658664.3659647","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3658664.3659647","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018100486","display_name":"Taiba Majid Wani","orcid":"https://orcid.org/0000-0002-2335-0420"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Taiba Majid Wani","raw_affiliation_strings":["Sapienza University of Rome, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2335-0420","affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082721846","display_name":"Syed Asif Ahmad Qadri","orcid":"https://orcid.org/0000-0002-2060-1407"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Syed Asif Ahmad Qadri","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-2060-1407","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019647783","display_name":"Danilo Comminiello","orcid":"https://orcid.org/0000-0003-4067-4504"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Danilo Comminiello","raw_affiliation_strings":["Sapienza University of Rome, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4067-4504","affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030121038","display_name":"Irene Amerini","orcid":"https://orcid.org/0000-0002-6461-1391"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Irene Amerini","raw_affiliation_strings":["Sapienza University of Rome, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6461-1391","affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"271","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991999864578247,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9919999837875366,"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/concatenation","display_name":"Concatenation (mathematics)","score":0.9093623161315918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7901639938354492},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6041982173919678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5260602831840515},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4558301568031311},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3883506953716278},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3449481725692749},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05347764492034912}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.9093623161315918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7901639938354492},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6041982173919678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5260602831840515},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4558301568031311},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3883506953716278},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3449481725692749},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05347764492034912},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3658664.3659647","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658664.3659647","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1714014","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1714014","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3658664.3659647","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658664.3659647","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2922490899","https://openalex.org/W2936802426","https://openalex.org/W2967606780","https://openalex.org/W2989571531","https://openalex.org/W3008818273","https://openalex.org/W3026777299","https://openalex.org/W3082451925","https://openalex.org/W3135508679","https://openalex.org/W3216721989","https://openalex.org/W4280549751","https://openalex.org/W4293092748","https://openalex.org/W4298394324","https://openalex.org/W4298635730","https://openalex.org/W4312743281","https://openalex.org/W4317358019","https://openalex.org/W4386432956","https://openalex.org/W4389914235","https://openalex.org/W4391229131","https://openalex.org/W4392153109"],"related_works":["https://openalex.org/W4386159726","https://openalex.org/W2601157893","https://openalex.org/W2131735617","https://openalex.org/W2373006798","https://openalex.org/W2056912418","https://openalex.org/W2123759770","https://openalex.org/W2033213769","https://openalex.org/W4312376745","https://openalex.org/W2136016640","https://openalex.org/W2082269393"],"abstract_inverted_index":{"Audio":[0],"deepfake":[1,26,60],"detection":[2],"is":[3,65],"emerging":[4],"as":[5,12],"a":[6,43,72,102,116],"crucial":[7],"field":[8],"in":[9,126],"digital":[10],"media,":[11],"distinguishing":[13],"real":[14],"audio":[15,61,127,140],"from":[16],"deepfakes":[17],"becomes":[18],"increasingly":[19],"challenging":[20],"due":[21],"to":[22,119],"the":[23,68,96,147,162],"advancement":[24],"of":[25,71,75,135],"technologies.":[27],"These":[28],"methods":[29],"threaten":[30],"information":[31],"authenticity":[32],"and":[33,52,90,123,138,150,155],"pose":[34],"serious":[35],"security":[36],"risks.":[37],"Addressing":[38],"this":[39],"challenge,":[40],"we":[41],"propose":[42],"novel":[44],"architecture":[45],"that":[46],"combines":[47],"Convolutional":[48],"Neural":[49],"Networks":[50],"(CNN)":[51],"Bidirectional":[53],"Long":[54],"Short-Term":[55],"Memory":[56],"(BiLSTM)":[57],"for":[58,110,161],"effective":[59],"detection.":[62],"Our":[63],"approach":[64],"distinguished":[66],"by":[67,101,115],"feature":[69],"concatenation":[70],"comprehensive":[73,111],"set":[74],"acoustic":[76],"features:":[77],"Mel":[78,83],"Frequency":[79],"Cepstral":[80,87],"Coefficients":[81,88],"(MFCC),":[82],"spectrograms,":[84],"Constant":[85],"Q":[86],"(CQCC),":[89],"Constant-Q":[91],"Transform":[92],"(CQT)":[93],"vectors.":[94],"In":[95],"proposed":[97],"architecture,":[98],"features":[99,109],"processed":[100],"CNN":[103],"are":[104],"concatenated":[105],"into":[106],"two":[107],"multi-dimensional":[108],"analysis,":[112],"then":[113],"analyzed":[114],"BiLSTM":[117],"network":[118],"capture":[120],"temporal":[121],"dynamics":[122],"contextual":[124],"dependencies":[125],"data.":[128],"This":[129],"synergistic":[130],"method":[131],"ensures":[132],"an":[133],"understanding":[134],"both":[136],"spatial":[137],"sequential":[139],"characteristics.":[141],"We":[142],"validate":[143],"our":[144],"model":[145],"on":[146],"ASVSpoof":[148],"2019":[149],"FoR":[151],"datasets,":[152],"using":[153],"accuracy":[154],"Equal":[156],"Error":[157],"Rate":[158],"(EER)":[159],"metrics":[160],"evaluation.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}