{"id":"https://openalex.org/W4411377616","doi":"https://doi.org/10.1145/3733102.3736706","title":"Robust Multilingual Audio Deepfake Detection Through Hybrid Modeling","display_name":"Robust Multilingual Audio Deepfake Detection Through Hybrid Modeling","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411377616","doi":"https://doi.org/10.1145/3733102.3736706"},"language":"en","primary_location":{"id":"doi:10.1145/3733102.3736706","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3733102.3736706","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3733102.3736706","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3733102.3736706","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005680805","display_name":"Candy Olivia Mawalim","orcid":"https://orcid.org/0000-0001-9853-8893"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Candy Olivia Mawalim","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9853-8893","affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yutong Wang","orcid":"https://orcid.org/0009-0000-0110-9153"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yutong Wang","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Japan"],"raw_orcid":"https://orcid.org/0009-0000-0110-9153","affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114331340","display_name":"Aulia Adila","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aulia Adila","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Japan"],"raw_orcid":"https://orcid.org/0009-0002-2518-5665","affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080920610","display_name":"Shogo Okada","orcid":"https://orcid.org/0000-0002-9260-0403"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shogo Okada","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9260-0403","affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6605-2052","affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"181","last_page":"192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9979000091552734,"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":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.7863919138908386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36182111501693726},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34127071499824524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863919138908386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36182111501693726},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34127071499824524}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3733102.3736706","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3733102.3736706","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3733102.3736706","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3733102.3736706","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3733102.3736706","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3733102.3736706","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2647930541","display_name":"Unbreakable Speech: How to Create Enriched, Perceptually Robust Speech","funder_award_id":"25H01139","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6204560417","display_name":"Deepfake Detection for a Trustworthy Speech Communication","funder_award_id":"25K21245","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6265994423","display_name":"Voice information-hiding/anonymization technology for voice privacy protection","funder_award_id":"23K18491","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411377616.pdf","grobid_xml":"https://content.openalex.org/works/W4411377616.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2123299109","https://openalex.org/W2176804518","https://openalex.org/W2807325376","https://openalex.org/W2936802426","https://openalex.org/W2963242190","https://openalex.org/W2964002616","https://openalex.org/W2967606780","https://openalex.org/W2989571531","https://openalex.org/W3026777299","https://openalex.org/W3095410713","https://openalex.org/W3163596559","https://openalex.org/W3196117288","https://openalex.org/W3197358873","https://openalex.org/W3198533616","https://openalex.org/W3201773091","https://openalex.org/W3209984917","https://openalex.org/W3211424380","https://openalex.org/W3213029956","https://openalex.org/W4221138880","https://openalex.org/W4225302959","https://openalex.org/W4297841787","https://openalex.org/W4311591887","https://openalex.org/W4367046815","https://openalex.org/W4381198892","https://openalex.org/W4386302282","https://openalex.org/W4389943989","https://openalex.org/W4401042610","https://openalex.org/W4402112137","https://openalex.org/W4402501105","https://openalex.org/W4402670026","https://openalex.org/W4404160901","https://openalex.org/W4404396197","https://openalex.org/W4405633805","https://openalex.org/W4405783426","https://openalex.org/W4406266021","https://openalex.org/W4406803348","https://openalex.org/W4406858673"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"increasing":[1],"sophistication":[2],"of":[3,49,64,94,114],"AI-generated":[4],"human":[5],"voice":[6],"poses":[7],"a":[8,34,53,61,85,105],"significant":[9],"threat,":[10],"demanding":[11],"robust":[12],"detection":[13,51,87],"systems":[14],"that":[15,89],"can":[16],"generalize":[17],"effectively":[18],"across":[19,138],"diverse":[20,81],"linguistic":[21],"environments":[22],"and":[23,60,67,75,97,141],"synthesis":[24,65,143],"techniques.In":[25],"response":[26],"to":[27,37,71],"the":[28,46,92,112],"SAFE":[29],"Challenge,":[30],"this":[31,80],"paper":[32],"introduces":[33],"novel":[35],"approach":[36],"multilingual":[38,54,106,139],"audio":[39,131],"deepfake":[40,50],"detection.Our":[41],"primary":[42],"contribution":[43],"lies":[44],"in":[45,118,129],"comprehensive":[47],"study":[48],"using":[52],"speech":[55],"corpus":[56],"encompassing":[57],"17":[58],"languages":[59],"broad":[62],"spectrum":[63],"methods":[66],"acoustic":[68],"conditions,":[69],"designed":[70],"enable":[72],"more":[73],"realistic":[74],"challenging":[76],"evaluations.To":[77],"optimally":[78],"utilize":[79],"data,":[82],"we":[83,110],"propose":[84],"hybrid":[86],"model":[88],"synergistically":[90],"combines":[91],"strengths":[93],"end-to-end":[95],"RawNet":[96],"AASIST":[98],"architectures":[99],"with":[100],"language-agnostic":[101],"representations":[102],"learned":[103],"from":[104],"selfsupervised":[107],"learning":[108],"model.Additionally,":[109],"explore":[111],"efficacy":[113],"RawBoost":[115],"data":[116,140],"augmentation":[117],"enhancing":[119],"robustness":[120],"against":[121],"realworld":[122],"noise.Our":[123],"experimental":[124],"evaluation":[125],"demonstrates":[126],"promising":[127],"generalization":[128],"generated":[130],"detection,":[132],"achieving":[133],"approximately":[134],"73%":[135],"balanced":[136],"accuracy":[137],"unseen":[142],"algorithms.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}