{"id":"https://openalex.org/W4416677031","doi":"https://doi.org/10.1109/dsaa65442.2025.11247976","title":"Generalization in Audio Deepfake Detection: Evaluating ASR Encoder-Based Feature Extraction","display_name":"Generalization in Audio Deepfake Detection: Evaluating ASR Encoder-Based Feature Extraction","publication_year":2025,"publication_date":"2025-10-09","ids":{"openalex":"https://openalex.org/W4416677031","doi":"https://doi.org/10.1109/dsaa65442.2025.11247976"},"language":"en","primary_location":{"id":"doi:10.1109/dsaa65442.2025.11247976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa65442.2025.11247976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA)","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/A5062026425","display_name":"Karla Sch\u00e4fer","orcid":"https://orcid.org/0009-0004-1731-7925"},"institutions":[{"id":"https://openalex.org/I4210133470","display_name":"Fraunhofer Institute for Secure Information Technology","ror":"https://ror.org/03qt2gs44","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210133470","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Karla Sch\u00e4fer","raw_affiliation_strings":["Fraunhofer SIT, ATHENE,Darmstadt,Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer SIT, ATHENE,Darmstadt,Germany","institution_ids":["https://openalex.org/I4210133470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056579435","display_name":"Martin Steinebach","orcid":"https://orcid.org/0000-0002-0240-0388"},"institutions":[{"id":"https://openalex.org/I4210133470","display_name":"Fraunhofer Institute for Secure Information Technology","ror":"https://ror.org/03qt2gs44","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210133470","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Steinebach","raw_affiliation_strings":["Fraunhofer SIT, ATHENE,Darmstadt,Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer SIT, ATHENE,Darmstadt,Germany","institution_ids":["https://openalex.org/I4210133470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062026425"],"corresponding_institution_ids":["https://openalex.org/I4210133470"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20240858,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6796000003814697,"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":0.6796000003814697,"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":0.1307000070810318,"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":0.043699998408555984,"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/generalization","display_name":"Generalization","score":0.6578999757766724},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5733000040054321},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5546000003814697},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5504999756813049},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5436999797821045},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5390999913215637},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5389000177383423},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5156999826431274},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4936999976634979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355999946594238},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7056999802589417},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6578999757766724},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5733000040054321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5720000267028809},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5546000003814697},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5504999756813049},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.31450000405311584},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/dsaa65442.2025.11247976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsaa65442.2025.11247976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/500052","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/500052","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2891145043","https://openalex.org/W2963460857","https://openalex.org/W3026777299","https://openalex.org/W3163596559","https://openalex.org/W3205644108","https://openalex.org/W3212117663","https://openalex.org/W3213029956","https://openalex.org/W4225527248","https://openalex.org/W4297841787","https://openalex.org/W4381198892","https://openalex.org/W4385822624","https://openalex.org/W4385823150","https://openalex.org/W4392910562"],"related_works":[],"abstract_inverted_index":{"Audio":[0],"deepfakes":[1],"are":[2,8],"artificially":[3],"generated":[4],"audio":[5,48],"recordings":[6,32],"that":[7],"used":[9],"to":[10],"create":[11],"inauthentic":[12],"imitations":[13],"of":[14,21,25,30,40,64,104,110,133,161,172,191],"a":[15,44,117,169],"person's":[16],"utterances.":[17],"In":[18],"the":[19,22,28,38,41,81,84,93,101,105,108,136,141,180,188,192],"context":[20],"increasing":[23],"utilisation":[24],"artificial":[26],"intelligence,":[27],"recognition":[29,67],"these":[31],"is":[33,43],"becoming":[34],"increasingly":[35],"important.":[36],"Thereby,":[37],"generalization":[39],"detectors":[42],"major":[45],"challenge":[46],"in":[47,183],"deepfake":[49],"detection":[50],"(ADD).":[51],"We":[52],"analysed":[53,107],"six":[54],"feature":[55],"representations:":[56],"MFCC,":[57],"LFCC,":[58],"Wav2Vec2.0":[59],"and":[60,90,115,168],"three":[61],"pre-trained":[62],"encoders":[63,122],"automatic":[65],"speech":[66],"(ASR)":[68],"systems":[69],"(Whisper,":[70],"SpeechT5,":[71],"Canary)":[72],"for":[73],"ADD.":[74],"For":[75],"evaluating":[76],"their":[77],"generalizability,":[78],"we":[79,99],"trained":[80],"models":[82],"on":[83,92,135],"ASVspoof":[85],"2019":[86],"LA":[87],"train":[88],"set":[89,139],"tested":[91],"in-the-wild":[94],"(ITW)":[95],"test":[96,138],"set.":[97],"Furthermore,":[98],"evaluated":[100],"training":[102,113,143,166,170,185],"time":[103,144,171],"models,":[106],"effect":[109],"additional":[111,165],"(newer)":[112],"data":[114],"performed":[116],"correlation":[118],"analysis.":[119],"The":[120,149],"ASR":[121],"were":[123,152],"outperformed":[124],"by":[125],"using":[126,154,164],"simple":[127],"MFCC":[128],"features,":[129],"achieving":[130],"an":[131,159],"EER":[132,160],"17.96%":[134],"ITW":[137],"with":[140,158],"lowest":[142],"(7":[145],"min.":[146,174],"per":[147,175],"epoch).":[148],"best":[150,189],"results":[151],"calculated":[153],"Wav2Vec":[155,177],"2.0":[156],"(+MFCC)":[157],"17.60%,":[162],"but":[163],"data,":[167],"135":[173],"epoch.":[176],"also":[178],"showed":[179],"highest":[181],"correlations":[182],"varying":[184],"settings,":[186],"indicating":[187],"predictability":[190],"model's":[193],"performance.":[194]},"counts_by_year":[],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-11-25T00:00:00"}