{"id":"https://openalex.org/W4408355632","doi":"https://doi.org/10.1109/icassp49660.2025.10889257","title":"Strong Alone, Stronger Together: Synergizing Modality-Binding Foundation Models with Optimal Transport for Non-Verbal Emotion Recognition","display_name":"Strong Alone, Stronger Together: Synergizing Modality-Binding Foundation Models with Optimal Transport for Non-Verbal Emotion Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355632","doi":"https://doi.org/10.1109/icassp49660.2025.10889257"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5076790933","display_name":"Orchid Chetia Phukan","orcid":"https://orcid.org/0000-0002-2542-8084"},"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/A5113394151","display_name":"Mohd Mujtaba Akhtar","orcid":"https://orcid.org/0009-0000-1982-7110"},"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":"Mohd Mujtaba Akhtar","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/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/A5014658425","display_name":"Swarup Ranjan Behera","orcid":null},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Swarup Ranjan Behera","raw_affiliation_strings":["Reliance Jio AICoE,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reliance Jio AICoE,India","institution_ids":["https://openalex.org/I4210136064"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034547622","display_name":"Sishir Kalita","orcid":"https://orcid.org/0009-0005-9850-3953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sishir Kalita","raw_affiliation_strings":["Armsoftech.air,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Armsoftech.air,India","institution_ids":[]}]},{"author_position":"middle","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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715704","display_name":"Rajesh Sharma","orcid":"https://orcid.org/0000-0001-6308-2371"},"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":"Rajesh Sharma","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":"last","author":{"id":"https://openalex.org/A5052129812","display_name":"S. R. Mahadeva Prasanna","orcid":"https://orcid.org/0000-0002-8135-7938"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S.R Mahadeva Prasanna","raw_affiliation_strings":["IIT-Dharwad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT-Dharwad,India","institution_ids":["https://openalex.org/I4210152718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9785000085830688,"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":0.9785000085830688,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9739999771118164,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6543388366699219},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5889477729797363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5690674781799316},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4563158452510834},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4209247827529907},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.40942785143852234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30187270045280457},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3008841872215271}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6543388366699219},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5889477729797363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5690674781799316},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4563158452510834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4209247827529907},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.40942785143852234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30187270045280457},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3008841872215271},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1995663108","https://openalex.org/W2030931454","https://openalex.org/W3158929093","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3205872166","https://openalex.org/W3206252155","https://openalex.org/W3209984917","https://openalex.org/W4210836801","https://openalex.org/W4225635674","https://openalex.org/W4297841583","https://openalex.org/W4372259780","https://openalex.org/W4375869379","https://openalex.org/W4385822494","https://openalex.org/W4386071707","https://openalex.org/W4388366327","https://openalex.org/W4391454536","https://openalex.org/W4400621920","https://openalex.org/W4401042610","https://openalex.org/W6780218876","https://openalex.org/W6856659047"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,57,102,124],"investigate":[4,75],"multimodal":[5],"foundation":[6,50,81],"models":[7,51],"(MFMs)":[8],"for":[9,141],"emotion":[10,33],"recognition":[11,34,94],"from":[12,60],"non-verbal":[13,31],"sounds.":[14],"We":[15,73],"hypothesize":[16],"that":[17,44],"MFMs,":[18],"with":[19,116,129],"their":[20],"joint":[21],"pre-training":[22],"across":[23],"multiple":[24],"modalities,":[25],"will":[26],"be":[27,46],"more":[28],"effective":[29],"in":[30,48,92],"sounds":[32],"(NVER)":[35],"by":[36,90],"better":[37],"interpreting":[38],"and":[39,64,66,95,122,135,144,150,154],"differentiating":[40],"subtle":[41],"emotional":[42],"cues":[43],"may":[45],"ambiguous":[47],"audio-only":[49],"(AFMs).":[52],"To":[53,99],"validate":[54],"our":[55],"hypothesis,":[56],"extract":[58],"representations":[59,84],"state-of-the-art":[61],"(SOTA)":[62],"MFMs":[63],"AFMs":[65],"evaluated":[67],"them":[68],"on":[69,157],"benchmark":[70,159],"NVER":[71,87],"datasets.":[72,160],"also":[74],"the":[76,117,126,158],"potential":[77],"of":[78,119,131,137],"combining":[79],"selected":[80],"model":[82],"(FM)":[83],"to":[85],"enhance":[86],"further":[88],"inspired":[89],"research":[91],"speech":[93],"audio":[96],"deepfake":[97],"detection.":[98],"achieve":[100],"this,":[101],"propose":[103],"a":[104],"framework":[105],"called":[106],"MATA":[107,114],"(Intra-Modality":[108],"Alignment":[109],"through":[110],"Transport":[111],"Attention).":[112],"Through":[113],"coupled":[115],"combination":[118],"MFMs:":[120],"LanguageBind":[121],"ImageBind,":[123],"report":[125,155],"topmost":[127],"performance":[128],"accuracies":[130],"76.47%,":[132],"77.40%,":[133],"75.12%":[134],"F1-scores":[136],"70.35%,":[138],"76.19%,":[139],"74.63%":[140],"ASVP-ESD,":[142],"JNV,":[143],"VIVAE":[145],"datasets":[146],"against":[147],"individual":[148],"FMs":[149],"baseline":[151],"fusion":[152],"techniques":[153],"SOTA":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}