{"id":"https://openalex.org/W7148320387","doi":"https://doi.org/10.1109/asru65441.2025.11434709","title":"Post-training for Deepfake Speech Detection","display_name":"Post-training for Deepfake Speech Detection","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148320387","doi":"https://doi.org/10.1109/asru65441.2025.11434709"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5051909763","display_name":"Wanying Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Wanying Ge","raw_affiliation_strings":["National Institute of Informatics,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132816288","display_name":"Xuechen Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xuechen Liu","raw_affiliation_strings":["National Institute of Informatics,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051909763"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":4.3637,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95467577,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.5619999766349792,"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":0.5619999766349792,"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":0.31520000100135803,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.020899999886751175,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6294000148773193},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5920000076293945},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.516700029373169},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.43619999289512634},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.40049999952316284},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3668000102043152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146999835968018},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6294000148773193},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5920000076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5641000270843506},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5333999991416931},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.516700029373169},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.40049999952316284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37880000472068787},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.335999995470047},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.3190000057220459},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.27970001101493835}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.611548662185669,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2923014074","https://openalex.org/W2925618549","https://openalex.org/W2972359262","https://openalex.org/W2989571531","https://openalex.org/W3026777299","https://openalex.org/W3095410713","https://openalex.org/W3163596559","https://openalex.org/W3197358873","https://openalex.org/W3198429080","https://openalex.org/W3198533616","https://openalex.org/W3201773091","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3211424380","https://openalex.org/W3212117663","https://openalex.org/W3213029956","https://openalex.org/W4206908380","https://openalex.org/W4225527248","https://openalex.org/W4296068974","https://openalex.org/W4297841787","https://openalex.org/W4313306150","https://openalex.org/W4319862245","https://openalex.org/W4319862635","https://openalex.org/W4367046815","https://openalex.org/W4372266958","https://openalex.org/W4385245566","https://openalex.org/W4385822952","https://openalex.org/W4385823033","https://openalex.org/W4385823191","https://openalex.org/W4392910562","https://openalex.org/W4394862910","https://openalex.org/W4401437283","https://openalex.org/W4402111490","https://openalex.org/W4402111622","https://openalex.org/W4402111996","https://openalex.org/W4402112414","https://openalex.org/W4402116004","https://openalex.org/W4402351686","https://openalex.org/W4403791925","https://openalex.org/W4403955716","https://openalex.org/W4403956249","https://openalex.org/W4405181438","https://openalex.org/W4405182531","https://openalex.org/W4405272334","https://openalex.org/W4406138340","https://openalex.org/W4406345321","https://openalex.org/W4406461435","https://openalex.org/W4408144899","https://openalex.org/W4408345737","https://openalex.org/W4408355254","https://openalex.org/W4412945512","https://openalex.org/W4415707876","https://openalex.org/W4415708947"],"related_works":[],"abstract_inverted_index":{"We":[0,25],"introduce":[1],"a":[2,29,36],"post-training":[3],"approach":[4],"that":[5,72,102],"adapts":[6],"self-supervised":[7],"learning":[8],"(SSL)":[9],"models":[10,33,75,96],"for":[11],"deepfake":[12,84],"speech":[13,39,51,60],"detection":[14],"by":[15],"bridging":[16],"the":[17,73,92],"gap":[18],"between":[19],"general":[20],"pre-training":[21],"and":[22,52,80,111],"domain-specific":[23],"fine-tuning.":[24],"present":[26],"AntiDeepfake":[27],"models,":[28],"series":[30],"of":[31,49,59],"post-trained":[32,74],"developed":[34],"using":[35],"large-scale":[37],"multilingual":[38],"dataset":[40],"containing":[41],"over":[42,65],"$\\mathbf{5":[43],"6,":[44],"0":[45,46,55,56],"0}$":[47,57],"hours":[48,58],"genuine":[50],"$\\mathbf{1":[53],"8,":[54],"with":[61],"various":[62],"artifacts":[63],"in":[64],"one":[66],"hundred":[67],"languages.":[68],"Experimental":[69],"results":[70],"show":[71],"already":[76],"exhibit":[77],"strong":[78],"robustness":[79],"generalization":[81],"to":[82],"unseen":[83],"speech.":[85],"When":[86],"they":[87],"are":[88,116],"further":[89],"fine-tuned":[90],"on":[91],"Deepfake-Eval-2024":[93],"dataset,":[94],"these":[95],"consistently":[97],"surpass":[98],"existing":[99],"state-of-the-art":[100],"detectors":[101],"do":[103],"not":[104],"leverage":[105],"post-training.":[106],"Model":[107],"checkpoint<sup":[108],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[109,114,119,125],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[110],"source":[112],"code<sup":[113],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[115],"available":[117],"online.<sup":[118],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Zenodo:":[120],"https://doi.org/10.5281/zenodo.15580542":[121],"Hugging":[122],"Face:":[123],"https://huggingface.co/nii-yamagishilab<sup":[124],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>GitHub:":[126],"https://github.com/nii-yamagishilab/AntiDeepfake":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}