{"id":"https://openalex.org/W4408355678","doi":"https://doi.org/10.1109/icassp49660.2025.10889665","title":"Multi-Relational Geometric Regularization Framework for Multi-Modal Emotion Recognition in Conversation","display_name":"Multi-Relational Geometric Regularization Framework for Multi-Modal Emotion Recognition in Conversation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355678","doi":"https://doi.org/10.1109/icassp49660.2025.10889665"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889665","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/A5100375762","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-0432-2942"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Software College of Northeastern University,Shenyang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software College of Northeastern University,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009338378","display_name":"Zhenhua Tan","orcid":"https://orcid.org/0000-0002-9870-8925"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Tan","raw_affiliation_strings":["Software College of Northeastern University,Shenyang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software College of Northeastern University,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9224756"],"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":0.9602000117301941,"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":0.9602000117301941,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.8099615573883057},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7403181195259094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6701284050941467},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5524425506591797},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4873834252357483},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4600496292114258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44769445061683655},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40080526471138},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14597734808921814},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.13475722074508667}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8099615573883057},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7403181195259094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6701284050941467},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5524425506591797},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4873834252357483},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4600496292114258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44769445061683655},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40080526471138},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14597734808921814},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.13475722074508667},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889665","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":0.4000000059604645,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2085662862","https://openalex.org/W2146334809","https://openalex.org/W2805662932","https://openalex.org/W2891359673","https://openalex.org/W2936162287","https://openalex.org/W2964300796","https://openalex.org/W2965453734","https://openalex.org/W3045190208","https://openalex.org/W3098556456","https://openalex.org/W3173396651","https://openalex.org/W3211488063","https://openalex.org/W4376647221","https://openalex.org/W4385245566","https://openalex.org/W4385570630","https://openalex.org/W4385571916","https://openalex.org/W4386065863","https://openalex.org/W4386076442","https://openalex.org/W4392904377","https://openalex.org/W4392908930","https://openalex.org/W6766673545","https://openalex.org/W6767220426","https://openalex.org/W6796014657","https://openalex.org/W6797005690","https://openalex.org/W6810798621","https://openalex.org/W6855061154"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W1968552888","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W1511346092","https://openalex.org/W1527532029","https://openalex.org/W3105646692","https://openalex.org/W4387914125","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Existing":[0],"studies":[1],"on":[2,11,140,163],"multi-modal":[3,12],"emotion":[4,18],"recognition":[5],"in":[6,22,44,75,94],"conversation":[7,83,98,144],"(MMERC)":[8],"mainly":[9],"focus":[10],"fusion":[13],"and":[14,47,82,87,97,133,143,148],"context":[15],"modeling":[16],"for":[17,51,120],"representation,":[19],"facing":[20],"limitations":[21],"uncovering":[23],"the":[24,61,72,102,164,175],"intrinsic":[25],"structure":[26],"of":[27,105,130,177],"emotion-related":[28],"data.":[29,67],"The":[30,168],"existing":[31],"geometric":[32,73,128],"consistency":[33,74,137],"regularization":[34,138],"(GCR)":[35],"technique":[36],"aims":[37],"to":[38,60,92],"build":[39],"meaningful":[40],"latent":[41],"feature":[42],"structures":[43,129],"multiple":[45,141],"modalities":[46],"has":[48],"been":[49],"validated":[50],"non-conversational":[52],"data,":[53],"therefore":[54],"we":[55,69,113],"further":[56],"explore":[57],"its":[58],"application":[59,104],"MMERC":[62,121,161],"task,":[63],"which":[64],"involves":[65],"conversational":[66,76,131],"However,":[68],"find":[70],"that":[71],"data":[77,132],"varies":[78],"among":[79],"different":[80],"speaker":[81,95,142],"relations":[84,145],"(intra-speaker,":[85,146],"inter-speaker,":[86],"inter-conversation":[88,149],"relations),":[89],"probably":[90],"due":[91],"differences":[93],"expressions":[96],"topics.":[99],"This":[100],"makes":[101],"direct":[103],"GCR":[106],"less":[107],"effective.":[108],"To":[109],"address":[110],"this":[111],"issue,":[112],"propose":[114],"a":[115],"Multi-Relational":[116],"Geometric":[117],"Regularization":[118],"Framework":[119],"(R<sup":[122],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[123,180],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">4</sup>-MMERC).":[124],"Our":[125],"framework":[126,154],"constructs":[127],"performs":[134],"dynamically":[135],"balanced":[136],"based":[139],"interspeaker,":[147],"relations).":[150],"We":[151],"tested":[152],"our":[153,178],"by":[155],"integrating":[156],"it":[157],"with":[158],"three":[159],"typical":[160],"models":[162],"IEMOCAP":[165],"benchmark":[166],"dataset.":[167],"results":[169],"show":[170],"significant":[171],"performance":[172],"improvements,":[173],"demonstrating":[174],"effectiveness":[176],"approach<sup":[179],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}