{"id":"https://openalex.org/W4416250999","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229087","title":"End-to-end Audio Deepfake Detection from RAW Waveforms: a RawNet-Based Approach with Cross-Dataset Evaluation","display_name":"End-to-end Audio Deepfake Detection from RAW Waveforms: a RawNet-Based Approach with Cross-Dataset Evaluation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250999","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229087"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229087","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/A5119897066","display_name":"Andrea Di Pierno","orcid":"https://orcid.org/0000-0002-6279-9212"},"institutions":[{"id":"https://openalex.org/I127077003","display_name":"IMT School for Advanced Studies Lucca","ror":"https://ror.org/035gh3a49","country_code":"IT","type":"education","lineage":["https://openalex.org/I127077003"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Andrea Di Pierno","raw_affiliation_strings":["IMT School of Advanced Studies Lucca,Lucca,Italy"],"affiliations":[{"raw_affiliation_string":"IMT School of Advanced Studies Lucca,Lucca,Italy","institution_ids":["https://openalex.org/I127077003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060702304","display_name":"Luca Guarnera","orcid":"https://orcid.org/0000-0001-8315-351X"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Guarnera","raw_affiliation_strings":["University of Catania,Department of Mathematics and Computer Science,Catania,Italy"],"affiliations":[{"raw_affiliation_string":"University of Catania,Department of Mathematics and Computer Science,Catania,Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019181839","display_name":"Dario Allegra","orcid":"https://orcid.org/0000-0002-4819-5340"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Dario Allegra","raw_affiliation_strings":["University of Catania,Department of Mathematics and Computer Science,Catania,Italy"],"affiliations":[{"raw_affiliation_string":"University of Catania,Department of Mathematics and Computer Science,Catania,Italy","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042746008","display_name":"Sebastiano Battiato","orcid":"https://orcid.org/0000-0001-6127-2470"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sebastiano Battiato","raw_affiliation_strings":["University of Catania,Department of Mathematics and Computer Science,Catania,Italy"],"affiliations":[{"raw_affiliation_string":"University of Catania,Department of Mathematics and Computer Science,Catania,Italy","institution_ids":["https://openalex.org/I39063666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5119897066"],"corresponding_institution_ids":["https://openalex.org/I127077003"],"apc_list":null,"apc_paid":null,"fwci":3.8676,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94367592,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.3799999952316284,"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":0.3799999952316284,"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":0.2928999960422516,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.04179999977350235,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5746999979019165},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5386999845504761},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.459199994802475},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44699999690055847},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4422000050544739},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38179999589920044},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.37929999828338623},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.3718000054359436},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.36809998750686646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345000147819519},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5746999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5712000131607056},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5386999845504761},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47380000352859497},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4422000050544739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40630000829696655},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.320499986410141},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.28610000014305115},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.27889999747276306},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229087","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1586405805","https://openalex.org/W2170505850","https://openalex.org/W2936802426","https://openalex.org/W2963351448","https://openalex.org/W2989571531","https://openalex.org/W3019200173","https://openalex.org/W3038930935","https://openalex.org/W3163596559","https://openalex.org/W4223569451","https://openalex.org/W4292828964","https://openalex.org/W4385822981","https://openalex.org/W4392623241","https://openalex.org/W4392902854","https://openalex.org/W4399801829","https://openalex.org/W4400350337","https://openalex.org/W4402112426","https://openalex.org/W4403791925","https://openalex.org/W4406138340","https://openalex.org/W4408054937","https://openalex.org/W4408353669","https://openalex.org/W4409751971"],"related_works":[],"abstract_inverted_index":{"Audio":[0],"deepfakes":[1],"represent":[2],"a":[3,71,91,161],"growing":[4],"threat":[5],"to":[6,15,76,104,130,154],"digital":[7],"security":[8],"and":[9,80,100,117,126,145,152,181,187,193],"trust,":[10],"leveraging":[11],"advanced":[12],"generative":[13],"models":[14,195],"produce":[16],"synthetic":[17],"speech":[18],"that":[19,61,94,113],"closely":[20],"mimics":[21],"real":[22],"human":[23],"voices.":[24],"Detecting":[25],"such":[26],"manipulations":[27,116],"is":[28,70],"especially":[29],"challenging":[30,162],"under":[31,134],"open-world":[32],"conditions,":[33],"where":[34],"spoofing":[35],"methods":[36],"encountered":[37],"during":[38,45],"testing":[39],"may":[40],"differ":[41],"from":[42,97],"those":[43],"seen":[44],"training.":[46],"In":[47],"this":[48],"work,":[49],"we":[50,89],"propose":[51],"an":[52],"end-to-end":[53],"deep":[54],"learning":[55],"framework":[56],"for":[57],"audio":[58,120,182,189],"deepfake":[59],"detection":[60],"operates":[62],"directly":[63],"on":[64,148,160],"raw":[65],"waveforms.":[66],"Our":[67],"model,":[68],"RawNetLite,":[69],"lightweight":[72],"convolutional-recurrent":[73],"architecture":[74],"designed":[75],"capture":[77],"both":[78],"spectral":[79],"temporal":[81],"features":[82],"without":[83],"handcrafted":[84],"preprocessing.":[85],"To":[86],"enhance":[87],"robustness,":[88],"introduce":[90],"training":[92,176],"strategy":[93],"combines":[95],"data":[96,150],"multiple":[98],"domains":[99],"adopts":[101],"Focal":[102],"Loss":[103],"emphasize":[105],"difficult":[106],"or":[107],"ambiguous":[108],"samples.":[109],"We":[110],"further":[111],"demonstrate":[112],"incorporating":[114],"codec-based":[115],"applying":[118],"waveform-level":[119],"augmentations":[121,183],"(e.g.,":[122],"pitch":[123],"shifting,":[124],"noise,":[125],"time":[127],"stretching)":[128],"leads":[129],"significant":[131],"generalization":[132],"improvements":[133],"realistic":[135],"acoustic":[136],"conditions.":[137],"The":[138],"proposed":[139],"model":[140],"achieves":[141],"over":[142],"99.7%":[143],"F1":[144,156],"0.25%":[146],"EER":[147,159],"in-domain":[149],"(FakeOrReal),":[151],"up":[153],"83.4%":[155],"with":[157],"16.4%":[158],"out-of-distribution":[163],"test":[164],"set":[165],"(AVSpoof2021":[166],"+":[167],"CodecFake).":[168],"These":[169],"findings":[170],"highlight":[171],"the":[172],"importance":[173],"of":[174],"diverse":[175],"data,":[177],"tailored":[178],"objective":[179],"functions":[180],"in":[184],"building":[185],"resilient":[186],"generalizable":[188],"forgery":[190],"detectors.":[191],"Code":[192],"pretrained":[194],"are":[196],"available":[197],"at":[198],"https://iplab.dmi.unict.it/mfs/Deepfakes/PaperRawNet2025/.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-11-14T00:00:00"}