{"id":"https://openalex.org/W4416286094","doi":"https://doi.org/10.1109/lsp.2025.3634032","title":"Multi-Scale Self-Supervised Learning for Efficient Audio Deepfake Detection","display_name":"Multi-Scale Self-Supervised Learning for Efficient Audio Deepfake Detection","publication_year":2025,"publication_date":"2025-11-17","ids":{"openalex":"https://openalex.org/W4416286094","doi":"https://doi.org/10.1109/lsp.2025.3634032"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3634032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3634032","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","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/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","Sapienza University of 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"]},{"raw_affiliation_string":"Sapienza University of 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","Sapienza University of 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"]},{"raw_affiliation_string":"Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31551966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"46","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.414900004863739,"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":0.414900004863739,"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":0.24740000069141388,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.10899999737739563,"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/spectrogram","display_name":"Spectrogram","score":0.7268000245094299},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7055000066757202},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5805000066757202},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5188999772071838},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5008999705314636},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4458000063896179},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.391400009393692},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.37880000472068787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8741000294685364},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7268000245094299},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7055000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6583999991416931},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5805000066757202},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5242999792098999},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.391400009393692},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33799999952316284},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2025.3634032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3634032","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1765779","is_oa":false,"landing_page_url":"https://hdl.handle.net/11573/1765779","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2471520273","https://openalex.org/W2963300588","https://openalex.org/W2989571531","https://openalex.org/W3026777299","https://openalex.org/W3161011913","https://openalex.org/W3163596559","https://openalex.org/W3197273793","https://openalex.org/W3197358873","https://openalex.org/W3201773091","https://openalex.org/W4372266958","https://openalex.org/W4372347465","https://openalex.org/W4381198892","https://openalex.org/W4392902854","https://openalex.org/W4392904324","https://openalex.org/W4392910532","https://openalex.org/W4392910535","https://openalex.org/W4394617057","https://openalex.org/W4402111467","https://openalex.org/W4403955261","https://openalex.org/W4404765990","https://openalex.org/W4409346863","https://openalex.org/W4413991433"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"vocoders":[1],"enable":[2],"highly":[3],"realistic":[4],"synthetic":[5],"speech":[6],"that":[7],"challenges":[8],"multimedia":[9],"authentication;":[10],"however,":[11],"existing":[12],"detection":[13],"approaches":[14],"suffer":[15],"from":[16,100],"limited":[17],"robustness":[18],"to":[19,102],"unseen":[20],"synthesis":[21],"methods":[22],"and":[23,59,70],"inadequate":[24],"deployment":[25],"readiness.":[26],"We":[27],"propose":[28],"MASD":[29,41,112],"(Multi-scale":[30],"Artifact-aware":[31],"Self-supervised":[32],"Deepfake":[33],"detector),":[34],"combining":[35],"multi-scale":[36],"SSL":[37],"with":[38,65],"handcrafted":[39],"features.":[40],"decomposes":[42],"spectrograms":[43],"into":[44],"three":[45],"frequency":[46],"bands,":[47],"processed":[48],"through":[49,73],"an":[50],"encoder":[51],"pretrained":[52],"using":[53],"masked":[54],"reconstruction,":[55],"contrastive":[56],"predictive":[57],"coding,":[58],"adversarial":[60,90],"vocoder":[61],"classification.":[62],"Features":[63],"fuse":[64],"phase":[66],"coherence,":[67],"spectral":[68],"flux,":[69],"high-frequency":[71],"energy":[72],"cross-attention,":[74],"classified":[75],"by":[76],"temperature-scaled":[77],"SVM.":[78],"Evaluation":[79],"on":[80],"ASVspoof":[81],"2019":[82],"LA":[83],"demonstrates":[84],"state-of-the-art":[85],"performance.":[86],"Ablation":[87],"studies":[88],"confirm":[89],"augmentation":[91],"as":[92,113],"the":[93],"primary":[94],"driver":[95],"of":[96],"robustness,":[97],"improving":[98],"EER":[99],"1.52%":[101],"0.39%,":[103],"while":[104],"zero-shot":[105],"cross-dataset":[106],"evaluation":[107],"validates":[108],"generalization":[109],"effectiveness,":[110],"establishing":[111],"a":[114],"practical":[115],"solution.":[116]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-11-17T00:00:00"}