{"id":"https://openalex.org/W4220856327","doi":"https://doi.org/10.1109/mmul.2022.3161411","title":"Emotion Recognition With Multimodal Transformer Fusion Framework Based on Acoustic and Lexical Information","display_name":"Emotion Recognition With Multimodal Transformer Fusion Framework Based on Acoustic and Lexical Information","publication_year":2022,"publication_date":"2022-03-23","ids":{"openalex":"https://openalex.org/W4220856327","doi":"https://doi.org/10.1109/mmul.2022.3161411"},"language":"en","primary_location":{"id":"doi:10.1109/mmul.2022.3161411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2022.3161411","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE MultiMedia","raw_type":"journal-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/A5055229622","display_name":"Lili Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lili Guo","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5526-0980","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8094-6861","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-9237-4821","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028251075","display_name":"Yahui Fu","orcid":"https://orcid.org/0000-0001-8379-5993"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahui Fu","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-8379-5993","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100612858","display_name":"Jiaxing Liu","orcid":"https://orcid.org/0000-0001-9691-8470"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxing Liu","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-9691-8470","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082274996","display_name":"Shifei Ding","orcid":"https://orcid.org/0000-0002-1391-2717"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shifei Ding","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1391-2717","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055229622"],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":3.459,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92404677,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"29","issue":"2","first_page":"94","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9954000115394592,"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/T11309","display_name":"Music and Audio Processing","score":0.9902999997138977,"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/paralanguage","display_name":"Paralanguage","score":0.9088037014007568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7982969284057617},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6328697800636292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5359846353530884},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5082089900970459},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.484771192073822},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.465537428855896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45843392610549927},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4360063672065735},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11014074087142944}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9088037014007568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982969284057617},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6328697800636292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5359846353530884},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5082089900970459},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.484771192073822},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.465537428855896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45843392610549927},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4360063672065735},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11014074087142944},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmul.2022.3161411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2022.3161411","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE MultiMedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G2162735739","display_name":null,"funder_award_id":"61976216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7732325329","display_name":null,"funder_award_id":"62176182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W147964346","https://openalex.org/W1534131679","https://openalex.org/W1832693441","https://openalex.org/W2053782908","https://openalex.org/W2085662862","https://openalex.org/W2146334809","https://openalex.org/W2696559478","https://openalex.org/W2766925079","https://openalex.org/W2889169802","https://openalex.org/W2937154351","https://openalex.org/W2939224318","https://openalex.org/W2963686995","https://openalex.org/W2963785564","https://openalex.org/W2997026866","https://openalex.org/W3016138882","https://openalex.org/W3035448883","https://openalex.org/W3120680448","https://openalex.org/W3183891373","https://openalex.org/W4299280181","https://openalex.org/W6748877103","https://openalex.org/W6750449527","https://openalex.org/W6761808342"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"People":[0],"usually":[1],"express":[2],"emotions":[3],"through":[4],"paralinguistic":[5,17],"and":[6,16,39,47,57,90,101,140],"linguistic":[7,15],"information":[8,18],"in":[9],"speech.":[10],"How":[11],"to":[12,36,64,99,115],"effectively":[13],"integrate":[14],"for":[19,70],"emotion":[20],"recognition":[21],"is":[22,113],"a":[23,44,51],"challenge.":[24],"Previous":[25],"studies":[26],"have":[27],"adopted":[28],"the":[29,55,96,110,117,132,147,151],"bidirectional":[30],"long":[31],"short-term":[32],"memory":[33],"(BLSTM)":[34],"network":[35],"extract":[37],"acoustic":[38,88],"lexical":[40],"representations":[41],"followed":[42],"by":[43],"concatenate":[45],"layer,":[46],"this":[48,74],"has":[49],"become":[50],"common":[52],"method.":[53,154],"However,":[54],"interaction":[56],"influence":[58],"between":[59],"different":[60,120],"modalities":[61,98],"are":[62],"difficult":[63],"promote":[65],"using":[66],"simple":[67],"feature":[68],"fusion":[69,83,112],"each":[71,103],"sentence.":[72],"In":[73],"article,":[75],"we":[76,123],"propose":[77],"an":[78],"implicitly":[79],"aligned":[80],"multimodal":[81,141],"transformer":[82],"(IA-MMTF)":[84],"framework":[85],"based":[86],"on":[87,131],"features":[89],"text":[91],"information.":[92],"This":[93],"model":[94],"enables":[95],"two":[97],"guide":[100],"complement":[102],"other":[104],"when":[105],"learning":[106],"emotional":[107,128,134],"representations.":[108,129],"Thereafter,":[109],"weighed":[111],"used":[114],"control":[116],"contributions":[118],"of":[119],"modalities.":[121],"Thus,":[122],"can":[124],"obtain":[125],"more":[126],"complementary":[127],"Experiments":[130],"interactive":[133],"dyadic":[135],"motion":[136],"capture":[137],"(IEMOCAP)":[138],"database":[139],"emotionlines":[142],"dataset":[143],"(MELD)":[144],"show":[145],"that":[146],"proposed":[148],"method":[149],"outperforms":[150],"baseline":[152],"BLSTM-based":[153]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}