{"id":"https://openalex.org/W4415481061","doi":"https://doi.org/10.1007/s10791-025-09746-4","title":"Dynamic knowledge condensation with audio-selective transformer for audio deepfake detection","display_name":"Dynamic knowledge condensation with audio-selective transformer for audio deepfake detection","publication_year":2025,"publication_date":"2025-10-23","ids":{"openalex":"https://openalex.org/W4415481061","doi":"https://doi.org/10.1007/s10791-025-09746-4"},"language":"en","primary_location":{"id":"doi:10.1007/s10791-025-09746-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-025-09746-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-025-09746-4.pdf","source":{"id":"https://openalex.org/S5407036663","display_name":"Discover Computing","issn_l":"2948-2992","issn":["2948-2992"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s10791-025-09746-4.pdf","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":true,"raw_author_name":"Taiba Maijd Wani","raw_affiliation_strings":["Department of Computer, Control and Management Engineering, Sapienza University of Rome, Piazzale Aldo Moro 5, 00185, Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer, Control and Management Engineering, Sapienza University of Rome, Piazzale Aldo Moro 5, 00185, 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":["Department of Computer, Control and Management Engineering, Sapienza University of Rome, Piazzale Aldo Moro 5, 00185, Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer, Control and Management Engineering, Sapienza University of Rome, Piazzale Aldo Moro 5, 00185, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5018100486"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34214081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.9962000250816345,"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/embedding","display_name":"Embedding","score":0.6100000143051147},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5644999742507935},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4634000062942505},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.3959999978542328},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.32350000739097595},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3012000024318695},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.2883000075817108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742000222206116},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6100000143051147},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5644999742507935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5317000150680542},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3734000027179718},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.32350000739097595},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10791-025-09746-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-025-09746-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-025-09746-4.pdf","source":{"id":"https://openalex.org/S5407036663","display_name":"Discover Computing","issn_l":"2948-2992","issn":["2948-2992"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f0fe576de38e46dbb8c462fbfcf0f44e","is_oa":true,"landing_page_url":"https://doaj.org/article/f0fe576de38e46dbb8c462fbfcf0f44e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Discover Computing, Vol 28, Iss 1, Pp 1-28 (2025)","raw_type":"article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1765784","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1765784","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/article"}],"best_oa_location":{"id":"doi:10.1007/s10791-025-09746-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-025-09746-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-025-09746-4.pdf","source":{"id":"https://openalex.org/S5407036663","display_name":"Discover Computing","issn_l":"2948-2992","issn":["2948-2992"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G507880695","display_name":null,"funder_award_id":"PE00000014","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415481061.pdf","grobid_xml":"https://content.openalex.org/works/W4415481061.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2571081683","https://openalex.org/W2936802426","https://openalex.org/W2989571531","https://openalex.org/W3112560676","https://openalex.org/W3163596559","https://openalex.org/W3177196641","https://openalex.org/W3201604899","https://openalex.org/W3213029956","https://openalex.org/W4225527248","https://openalex.org/W4293057051","https://openalex.org/W4297841727","https://openalex.org/W4313984387","https://openalex.org/W4381198892","https://openalex.org/W4387272110","https://openalex.org/W4392903665","https://openalex.org/W4393163378","https://openalex.org/W4394966980","https://openalex.org/W4395686273","https://openalex.org/W4399556751","https://openalex.org/W4402112039","https://openalex.org/W4402115975","https://openalex.org/W4404125290","https://openalex.org/W4404765990","https://openalex.org/W4405521770","https://openalex.org/W4405736291","https://openalex.org/W4405911176","https://openalex.org/W4406148177","https://openalex.org/W4408799803"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"The":[1,91],"rapid":[2],"evolution":[3],"of":[4,16,160,176],"audio":[5,66],"deepfakes":[6],"has":[7],"raised":[8],"significant":[9],"challenges":[10],"for":[11,64],"the":[12],"security":[13],"and":[14,88,103,120,123,145,152,162],"reliability":[15],"voice-driven":[17],"systems.":[18],"While":[19],"recent":[20],"detection":[21],"frameworks":[22],"achieve":[23],"high":[24],"accuracy":[25],"in":[26],"controlled":[27],"environments,":[28],"their":[29],"performance":[30,169],"often":[31],"degrades":[32],"under":[33,170,183],"real-world":[34],"conditions":[35],"involving":[36],"codec":[37,171],"compression,":[38],"signal":[39],"preprocessing,":[40],"or":[41],"domain":[42],"shifts.":[43],"To":[44,131],"address":[45],"these":[46],"challenges,":[47],"we":[48],"propose":[49],"dynamic":[50,101],"knowledge":[51,60],"condensation":[52],"with":[53,98],"audio-selective":[54,96],"transformer":[55,97],"(DK-CAST),":[56],"a":[57,71,81,94,126,137],"novel":[58],"tri-stream":[59],"distillation":[61],"framework":[62],"designed":[63],"robust":[65],"deepfake":[67],"detection.":[68],"DK-CAST":[69,134,166],"employs":[70,93],"high-capacity":[72],"XLS-R":[73],"teacher":[74],"trained":[75],"on":[76,86,143,149,178],"clean":[77],"speech":[78],"to":[79,106],"supervise":[80],"compact":[82],"student":[83,92],"model":[84],"operating":[85],"degraded":[87],"preprocessed":[89],"audio.":[90],"custom":[95],"dual-stream":[99],"encoding,":[100],"fusion,":[102],"phoneme-gated":[104],"attention":[105],"emphasize":[107],"linguistically":[108],"relevant":[109],"cues.":[110],"Knowledge":[111],"is":[112],"transferred":[113],"via":[114],"multi-level":[115],"supervision,":[116],"including":[117],"logits,":[118],"embeddings,":[119],"phoneme":[121],"posteriors,":[122],"modulated":[124],"through":[125],"codec-aware":[127],"loss":[128],"weighting":[129],"scheme.":[130],"enhance":[132],"generalization,":[133],"also":[135],"includes":[136],"compression-agnostic":[138],"embedding":[139],"alignment":[140],"module":[141],"based":[142],"MMD":[144],"Center":[146],"Loss.":[147],"Evaluations":[148],"ASVspoof":[150,153,179],"2019-LA":[151],"2021-DF":[154,180],"demonstrate":[155],"state-of-the-art":[156],"performance,":[157],"achieving":[158,173],"EERs":[159],"0.38":[161],"2.18%,":[163],"respectively.":[164],"Furthermore,":[165],"maintains":[167],"strong":[168],"degradation,":[172],"an":[174],"EER":[175],"3.01%":[177],"when":[181],"tested":[182],"MP3":[184],"compression.":[185]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-24T00:00:00"}