{"id":"https://openalex.org/W4415524420","doi":"https://doi.org/10.1109/mlsp62443.2025.11204297","title":"Hubert-Derived SSL Features and ECAPA-TDNN Matching for Robust Audio Deepfake Detection","display_name":"Hubert-Derived SSL Features and ECAPA-TDNN Matching for Robust Audio Deepfake Detection","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524420","doi":"https://doi.org/10.1109/mlsp62443.2025.11204297"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5073440516","display_name":"G\u00fcl Tahao\u011flu","orcid":"https://orcid.org/0000-0002-8828-5674"},"institutions":[{"id":"https://openalex.org/I162720556","display_name":"Karadeniz Technical University","ror":"https://ror.org/03z8fyr40","country_code":"TR","type":"education","lineage":["https://openalex.org/I162720556"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Gul Tahaoglu","raw_affiliation_strings":["Karadeniz Technical University,Department of Computer Engineering,Trabon,Turkey"],"affiliations":[{"raw_affiliation_string":"Karadeniz Technical University,Department of Computer Engineering,Trabon,Turkey","institution_ids":["https://openalex.org/I162720556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5073440516"],"corresponding_institution_ids":["https://openalex.org/I162720556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41216606,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9847000241279602,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9560999870300293,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.5806000232696533},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5559999942779541},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.45159998536109924},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4462999999523163},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4207000136375427},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.3709000051021576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971000075340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5924000144004822},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.5806000232696533},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.45159998536109924},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4462999999523163},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4235999882221222},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3815999925136566},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3084000051021576},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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":29,"referenced_works":["https://openalex.org/W2303197844","https://openalex.org/W2407170210","https://openalex.org/W2745442703","https://openalex.org/W2747182415","https://openalex.org/W2749090340","https://openalex.org/W2799053639","https://openalex.org/W2936802426","https://openalex.org/W2972884023","https://openalex.org/W2973231137","https://openalex.org/W3024869864","https://openalex.org/W3127781933","https://openalex.org/W3163596559","https://openalex.org/W3170179936","https://openalex.org/W3197134965","https://openalex.org/W3198370097","https://openalex.org/W3209059054","https://openalex.org/W3209552243","https://openalex.org/W3209984917","https://openalex.org/W3212117663","https://openalex.org/W4225420087","https://openalex.org/W4317358019","https://openalex.org/W4385224813","https://openalex.org/W4385823150","https://openalex.org/W4392910535","https://openalex.org/W4401609584","https://openalex.org/W4401748455","https://openalex.org/W4403054584","https://openalex.org/W4403331203","https://openalex.org/W4411120545"],"related_works":[],"abstract_inverted_index":{"The":[0,93],"rapid":[1],"advancement":[2],"and":[3,20,29,51,65,82,103,113],"growing":[4],"accessibility":[5],"of":[6,25,101,110,117],"deepfake":[7,38],"audio":[8,31,39],"technologies":[9],"have":[10],"prompted":[11],"substantial":[12],"concerns,":[13],"particularly":[14],"in":[15],"domains":[16],"such":[17],"as":[18],"politics":[19],"media,":[21],"regarding":[22],"the":[23,77,85],"reliability":[24],"distinguishing":[26],"between":[27],"authentic":[28],"manipulated":[30],"recordings.":[32],"This":[33],"study":[34],"proposes":[35],"a":[36,52,114],"robust":[37],"detection":[40],"framework":[41],"combining":[42],"selfsupervised":[43],"learning":[44],"(SSL)":[45],"features":[46],"extracted":[47],"using":[48],"HuBERT":[49,62],"models":[50],"powerful":[53],"ECAPA-TDNN":[54],"classifier":[55],"enhanced":[56],"with":[57,69,105],"One-Class":[58],"Softmax":[59],"(OC-Softmax).":[60],"Three":[61],"variants-Base,":[63],"Large,":[64],"XLarge-were":[66],"assessed,":[67],"along":[68],"various":[70],"fusion":[71,100],"strategies.":[72],"Experiments":[73],"were":[74],"conducted":[75],"on":[76,97],"ASVspoof":[78],"2019":[79],"LA":[80],"dataset":[81],"demonstrated":[83],"that":[84],"proposed":[86],"system":[87],"significantly":[88],"outperforms":[89],"existing":[90],"state-of-the-art":[91],"approaches.":[92],"best":[94],"configuration,":[95],"based":[96],"score":[98],"level":[99],"HuBERT-Large":[102],"HuBERT-XLarge":[104],"ECAPA-TDNN,":[106],"achieved":[107],"an":[108],"EER":[109],"0.20":[111],"%":[112],"minimum":[115],"t-DCF":[116],"0.006.":[118],"Available":[119],"at:":[120],"https://github.com/gultahaoglu/Hubertderiveredfeatures_deepfakeaudiodetection":[121]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}