{"id":"https://openalex.org/W4416799160","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249284","title":"Are Multimodal Foundation Models All That Is Needed for Emofake Detection?","display_name":"Are Multimodal Foundation Models All That Is Needed for Emofake Detection?","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799160","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249284"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5113394151","display_name":"Mohd Mujtaba Akhtar","orcid":"https://orcid.org/0009-0000-1982-7110"},"institutions":[{"id":"https://openalex.org/I170558118","display_name":"Sri Venkateswara University","ror":"https://ror.org/05weahn72","country_code":"IN","type":"education","lineage":["https://openalex.org/I170558118"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mohd Mujtaba Akhtar","raw_affiliation_strings":["V.B.S.P.U,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"V.B.S.P.U,India","institution_ids":["https://openalex.org/I170558118"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099056916","display_name":"Girish","orcid":null},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Girish","raw_affiliation_strings":["IIIT-Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099056917","display_name":"Orchid Chetia Phukan","orcid":null},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Orchid Chetia Phukan","raw_affiliation_strings":["IIIT-Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014658425","display_name":"Swarup Ranjan Behera","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swarup Ranjan Behera","raw_affiliation_strings":["Independent Researcher,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025920434","display_name":"Pailla Balakrishna Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I228011842","display_name":"Reliance Industries (United States)","ror":"https://ror.org/00jfs8131","country_code":"US","type":"company","lineage":["https://openalex.org/I228011842","https://openalex.org/I4210136064"]},{"id":"https://openalex.org/I4210136064","display_name":"Reliance Industries (India)","ror":"https://ror.org/04j6cfb03","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210136064"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Pailla Balakrishna Reddy","raw_affiliation_strings":["Reliance AI,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reliance AI,India","institution_ids":["https://openalex.org/I4210136064","https://openalex.org/I228011842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109582447","display_name":"A. NAYAK","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ananda Chandra Nayak","raw_affiliation_strings":["KAC,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAC,India","institution_ids":["https://openalex.org/I4210099236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001108774","display_name":"Sanjib Kumar Nayak","orcid":"https://orcid.org/0000-0001-9675-2853"},"institutions":[{"id":"https://openalex.org/I185065464","display_name":"Veer Surendra Sai University of Technology","ror":"https://ror.org/02yghbg68","country_code":"IN","type":"education","lineage":["https://openalex.org/I185065464"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sanjib Kumar Nayak","raw_affiliation_strings":["VSSUT,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VSSUT,India","institution_ids":["https://openalex.org/I185065464"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014100784","display_name":"Arun Balaji Buduru","orcid":"https://orcid.org/0000-0002-6267-8138"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arun Balaji Buduru","raw_affiliation_strings":["IIIT-Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4954,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87095008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"636","last_page":"641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.5059000253677368,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.5059000253677368,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.3206000030040741,"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":0.09920000284910202,"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/foundation","display_name":"Foundation (evidence)","score":0.7181000113487244},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5214999914169312},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.32580000162124634},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.26910001039505005}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7181000113487244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6607000231742859},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5214999914169312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5099999904632568},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39910000562667847},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2946000099182129},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.24269999563694}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2606361731","https://openalex.org/W3026777299","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4385822494","https://openalex.org/W4385823150","https://openalex.org/W4386071707","https://openalex.org/W4388821108","https://openalex.org/W4388821229","https://openalex.org/W4392902854","https://openalex.org/W4392908976","https://openalex.org/W4392910532","https://openalex.org/W4394019163","https://openalex.org/W4399793646","https://openalex.org/W4401042610","https://openalex.org/W4402111467","https://openalex.org/W4402112543","https://openalex.org/W4404822886","https://openalex.org/W4406461891","https://openalex.org/W4408354362","https://openalex.org/W4411120545"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,121],"work,":[2],"we":[3,70,101,123,175],"investigate":[4],"multimodal":[5],"foundation":[6,20,97],"models":[7,21,98],"(MFMs)":[8],"for":[9,93,129],"EmoFake":[10],"detection":[11,115],"(EFD)":[12],"and":[13,50,116,183,187],"hypothesize":[14],"that":[15,89],"they":[16],"will":[17],"outperform":[18],"audio":[19],"(AFMs).":[22],"MFMs":[23,43,79,90],"due":[24],"to":[25,147],"their":[26],"cross-modal":[27],"pre-training,":[28],"learns":[29],"emotional":[30,48,64],"patterns":[31],"from":[32,62,140],"multiple":[33],"modalities,":[34],"while":[35,165],"AFMs":[36,83,92],"rely":[37],"only":[38],"on":[39,190],"audio.":[40],"As":[41],"such,":[42],"can":[44],"better":[45],"recognize":[46],"unnatural":[47],"shifts":[49],"inconsistencies":[51],"in":[52,108],"manipulated":[53],"audio,":[54],"making":[55],"them":[56],"more":[57],"effective":[58,130],"at":[59,143],"distinguishing":[60],"real":[61],"fake":[63],"expressions.":[65],"To":[66,120],"validate":[67],"our":[68],"hypothesis,":[69],"conduct":[71],"a":[72,126,134,152],"comprehensive":[73],"comparative":[74],"analysis":[75],"of":[76,173],"state-of-the-art":[77],"(SOTA)":[78],"(e.g.":[80,84],"LanguageBind)":[81],"alongside":[82],"WavLM).":[85],"Our":[86],"experiments":[87],"confirm":[88],"surpass":[91],"EFD.":[94,191],"Beyond":[95],"individual":[96],"(FMs)":[99],"performance,":[100,178],"explore":[102],"FMs":[103,141,182],"fusion,":[104],"motivated":[105],"by":[106,160],"findings":[107],"related":[109],"research":[110],"areas":[111],"such":[112],"synthetic":[113],"speech":[114,117],"emotion":[118],"recognition.":[119],"end,":[122],"propose":[124],"SCAR,":[125],"novel":[127],"framework":[128],"fusion.":[131],"SCAR":[132,169],"introduces":[133],"nested":[135],"cross-attention":[136],"mechanism,":[137],"where":[138],"representations":[139,159],"interact":[142],"two":[144],"stages":[145],"sequentially":[146],"refine":[148],"information":[149],"exchange.":[150],"Additionally,":[151],"self-attention":[153],"refinement":[154],"module":[155],"further":[156],"enhances":[157],"feature":[158],"reinforcing":[161],"important":[162],"cross-FM":[163],"cues":[164],"suppressing":[166],"noise.":[167],"Through":[168],"with":[170],"synergistic":[171],"fusion":[172,185],"MFMs,":[174],"achieve":[176],"SOTA":[177],"surpassing":[179],"both":[180],"standalone":[181],"conventional":[184],"approaches":[186],"previous":[188],"works":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}