{"id":"https://openalex.org/W4395443988","doi":"https://doi.org/10.1145/3652583.3658086","title":"Retrieval-Augmented Audio Deepfake Detection","display_name":"Retrieval-Augmented Audio Deepfake Detection","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4395443988","doi":"https://doi.org/10.1145/3652583.3658086"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658086","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658086","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658086","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658086","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044640044","display_name":"Zuheng Kang","orcid":"https://orcid.org/0000-0001-9789-7798"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zuheng Kang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-9789-7798","affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095886691","display_name":"Yayun He","orcid":"https://orcid.org/0009-0008-9722-8031"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yayun He","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0008-9722-8031","affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082544347","display_name":"Botao Zhao","orcid":"https://orcid.org/0000-0001-9114-1236"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Botao Zhao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-9114-1236","affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586244","display_name":"Xiaoyang Qu","orcid":"https://orcid.org/0000-0001-8353-4064"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyang Qu","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-8353-4064","affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064443099","display_name":"Junqing Peng","orcid":"https://orcid.org/0009-0009-2903-9615"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junqing Peng","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0009-2903-9615","affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Insurance (Group) Company of China, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-9615-4749","affiliations":[{"raw_affiliation_string":"Ping An Insurance (Group) Company of China, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-9237-4231","affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5044640044"],"corresponding_institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4401726822"],"apc_list":null,"apc_paid":null,"fwci":3.617,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93627737,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"376","last_page":"384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991999864578247,"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":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.8397307395935059},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5898739099502563},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5353171825408936},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.46996232867240906},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44538983702659607},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.436404824256897},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.419176310300827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3974646329879761},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2413201630115509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8397307395935059},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5898739099502563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5353171825408936},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.46996232867240906},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44538983702659607},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.436404824256897},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.419176310300827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3974646329879761},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2413201630115509},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3652583.3658086","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658086","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658086","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.13892","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.13892","pdf_url":"https://arxiv.org/pdf/2404.13892","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658086","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658086","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658086","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3451530047","display_name":null,"funder_award_id":"2021B0101400003","funder_id":"https://openalex.org/F4320336405","funder_display_name":"Special Project for Research and Development in Key areas of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320336405","display_name":"Special Project for Research and Development in Key areas of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395443988.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2148154194","https://openalex.org/W2936802426","https://openalex.org/W2978329087","https://openalex.org/W3027879771","https://openalex.org/W3036601975","https://openalex.org/W3160325739","https://openalex.org/W3170179936","https://openalex.org/W3197134965","https://openalex.org/W3197358873","https://openalex.org/W3198329097","https://openalex.org/W3198486673","https://openalex.org/W3209984917","https://openalex.org/W3212117663","https://openalex.org/W4226264925","https://openalex.org/W4226346368","https://openalex.org/W4312743281","https://openalex.org/W4323022270","https://openalex.org/W4385823150","https://openalex.org/W4389328740","https://openalex.org/W6602661299"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559837139","https://openalex.org/W1151175420","https://openalex.org/W2407342067"],"abstract_inverted_index":{"With":[0],"recent":[1],"advances":[2],"in":[3,47],"speech":[4],"synthesis":[5],"including":[6],"text-to-speech":[7],"(TTS)":[8],"and":[9,50,114,120],"voice":[10],"conversion":[11],"(VC)":[12],"systems":[13],"enabling":[14],"the":[15,38,79,94,98,109,118,129,136,145],"generation":[16,56],"of":[17,97],"ultra-realistic":[18],"audio":[19],"deepfakes,":[20],"there":[21],"is":[22],"growing":[23],"concern":[24],"about":[25],"their":[26],"potential":[27],"misuse.":[28],"However,":[29],"most":[30],"deepfake":[31],"(DF)":[32],"detection":[33,62,150],"methods":[34],"rely":[35],"solely":[36],"on":[37,108,117],"fuzzy":[39],"knowledge":[40],"learned":[41],"by":[42,54],"a":[43,60],"single":[44],"model,":[45],"resulting":[46],"performance":[48,96],"bottlenecks":[49],"transparency":[51],"issues.":[52],"Inspired":[53],"retrieval-augmented":[55,61],"(RAG),":[57],"we":[58],"propose":[59],"(RAD)":[63],"framework":[64,101],"that":[65,128],"augments":[66],"test":[67],"samples":[68,72,133],"with":[69,86,139,144],"similar":[70],"retrieved":[71],"for":[73],"enhanced":[74],"detection.":[75],"We":[76],"also":[77],"extend":[78],"multi-fusion":[80],"attentive":[81],"classifier":[82],"to":[83],"integrate":[84],"it":[85],"our":[87],"proposed":[88,99],"RAD":[89,100],"framework.":[90],"Extensive":[91],"experiments":[92],"show":[93],"superior":[95],"over":[102],"baseline":[103],"methods,":[104],"achieving":[105],"state-of-the-art":[106],"results":[107,116],"ASVspoof":[110],"2021":[111,121],"DF":[112],"set":[113],"competitive":[115],"2019":[119],"LA":[122],"sets.":[123],"Further":[124],"sample":[125],"analysis":[126],"indicates":[127],"retriever":[130],"consistently":[131],"retrieves":[132],"mostly":[134],"from":[135],"same":[137],"speaker":[138],"acoustic":[140],"characteristics":[141],"highly":[142],"consistent":[143],"query":[146],"audio,":[147],"thereby":[148],"improving":[149],"performance.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}