{"id":"https://openalex.org/W4415539263","doi":"https://doi.org/10.1145/3746027.3755594","title":"WhiADD: Semantic-Acoustic Fusion for Robust Audio Deepfake Detection","display_name":"WhiADD: Semantic-Acoustic Fusion for Robust Audio Deepfake Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539263","doi":"https://doi.org/10.1145/3746027.3755594"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755594","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755594","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755594","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072771385","display_name":"Jianqiao Cui","orcid":"https://orcid.org/0000-0002-6016-5574"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianqiao Cui","raw_affiliation_strings":["Tsinghua University, Beijing, China and Yangtze Delta Region Institute of Tsinghua University, Zhejiang, Jiaxing, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China and Yangtze Delta Region Institute of Tsinghua University, Zhejiang, Jiaxing, Zhejiang, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013808212","display_name":"Bingyao Yu","orcid":"https://orcid.org/0000-0001-9550-6554"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingyao Yu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qihao Wang","orcid":"https://orcid.org/0009-0007-0612-7669"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihao Wang","raw_affiliation_strings":["GuangXi University, Nanning, GuangXi, China"],"affiliations":[{"raw_affiliation_string":"GuangXi University, Nanning, GuangXi, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fei Meng","orcid":"https://orcid.org/0000-0002-2553-9470"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Meng","raw_affiliation_strings":["Yangtze Delta Region Institute of Tsinghua University, Zhejiang, Jiaxing, China"],"affiliations":[{"raw_affiliation_string":"Yangtze Delta Region Institute of Tsinghua University, Zhejiang, Jiaxing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460385","display_name":"Jiwen Lu","orcid":"https://orcid.org/0000-0002-6121-5529"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiwen Lu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072771385"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38385291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11610","last_page":"11618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9947999715805054,"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":0.9947999715805054,"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":0.993399977684021,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/encoder","display_name":"Encoder","score":0.5282999873161316},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4864000082015991},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4239000082015991},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4147999882698059},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.39739999175071716},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.39640000462532043},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.34940001368522644},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.33149999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259000182151794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5503000020980835},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5282999873161316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49219998717308044},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.34940001368522644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3398999869823456},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755594","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755594","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755594","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755594","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2128435250","display_name":null,"funder_award_id":"No. 2023M741964","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2995181338","https://openalex.org/W3197358873","https://openalex.org/W4221138880","https://openalex.org/W4297498506","https://openalex.org/W4362467324","https://openalex.org/W4375869126"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,63,68,118,186],"critical":[4,187],"challenge":[5],"of":[6,103],"detecting":[7],"codec-based":[8,183],"audio":[9,36,115,198],"deepfakes":[10],"in":[11,150,197],"multilingual":[12,69],"and":[13,28,45,84,145,193],"dynamically":[14,112],"evolving":[15,182],"adversarial":[16],"scenarios.":[17],"While":[18],"existing":[19],"detection":[20,38,102,126,153],"systems":[21],"exhibit":[22],"performance":[23],"degradation":[24],"against":[25],"codec-generated":[26],"forgeries":[27],"unseen":[29],"linguistic":[30,96],"environments,":[31],"we":[32],"propose":[33],"a":[34,177],"novel":[35],"deepfake":[37],"framework":[39,158],"''WhiADD''":[40],"enhanced":[41],"by":[42,61,162],"semantic-acoustic":[43,172],"fusion":[44],"cross-modal":[46],"generalization.":[47],"Our":[48],"methodology":[49],"introduces":[50],"three":[51],"key":[52],"innovations:":[53],"(1)":[54],"The":[55,157],"Union":[56],"CodecFake":[57,64],"(UCF)":[58],"dataset,":[59],"synthesized":[60],"extending":[62],"generation":[65],"pipeline":[66],"to":[67,130,164,167],"Common":[70],"Voice":[71],"corpus,":[72],"significantly":[73],"expands":[74],"acoustic":[75,190],"diversity":[76],"with":[77,117],"1.9M":[78],"samples":[79],"across":[80],"varied":[81],"phonetic,":[82],"channel,":[83],"codec":[85],"manipulation":[86],"patterns.":[87],"(2)":[88],"A":[89,107],"semantic-prompted":[90],"Whisper":[91],"architecture":[92],"that":[93,111],"integrates":[94],"full-transcript":[95],"constraints":[97],"into":[98],"decoder":[99],"fine-tuning,":[100],"enabling":[101],"semantic":[104,194],"inconsistencies.":[105],"(3)":[106],"gated":[108],"cross-attention":[109],"mechanism":[110],"fuses":[113],"multi-source":[114],"features":[116],"proposed":[119],"model's":[120],"frozen":[121],"encoder":[122],"outputs,":[123],"enhancing":[124],"artifact":[125],"through":[127,170],"adaptive":[128],"attention":[129],"pre-trained":[131],"representations.":[132],"Extensive":[133],"experiments":[134],"demonstrate":[135],"state-of-the-art":[136],"performance,":[137],"achieving":[138],"0.55%":[139],"EER":[140,149],"on":[141],"UCF":[142],"testing":[143],"data":[144],"less":[146],"than":[147],"3%":[148],"zero-shot":[151],"cross-lingual":[152],"(German,":[154],"French,":[155],"Italian).":[156],"reduces":[159],"false":[160],"negatives":[161],"up":[163],"24%":[165],"compared":[166],"conventional":[168],"models":[169],"improved":[171],"alignment.":[173],"These":[174],"advancements":[175],"establish":[176],"robust":[178],"paradigm":[179],"for":[180],"combating":[181],"forgeries,":[184],"bridging":[185],"gap":[188],"between":[189],"feature":[191],"engineering":[192],"coherence":[195],"analysis":[196],"forensics.":[199]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}