{"id":"https://openalex.org/W4405709339","doi":"https://doi.org/10.1109/iscslp63861.2024.10800234","title":"Improving Emotion Recognition with Pre-Trained Models, Multimodality, and Contextual Information","display_name":"Improving Emotion Recognition with Pre-Trained Models, Multimodality, and Contextual Information","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709339","doi":"https://doi.org/10.1109/iscslp63861.2024.10800234"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":null,"display_name":"Zhengshun Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengshun Xia","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438492","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-0623-9114"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068357345","display_name":"Zhisheng Zheng","orcid":"https://orcid.org/0000-0001-7761-9790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhisheng Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.4846,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72440436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"636","last_page":"640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.697700023651123,"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":0.697700023651123,"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/multimodality","display_name":"Multimodality","score":0.9329230785369873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5946144461631775},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5433739423751831},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5011212825775146},{"id":"https://openalex.org/keywords/multimodal-therapy","display_name":"Multimodal therapy","score":0.4844103455543518},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.401214599609375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3949012756347656},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3485799729824066},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2949668765068054},{"id":"https://openalex.org/keywords/psychotherapist","display_name":"Psychotherapist","score":0.1515314280986786},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11139252781867981}],"concepts":[{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.9329230785369873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5946144461631775},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5433739423751831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5011212825775146},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.4844103455543518},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.401214599609375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3949012756347656},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3485799729824066},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2949668765068054},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.1515314280986786},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11139252781867981}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2108598243","https://openalex.org/W2146334809","https://openalex.org/W2912728762","https://openalex.org/W2946410230","https://openalex.org/W2963711448","https://openalex.org/W3001529617","https://openalex.org/W3097571315","https://openalex.org/W3192478068","https://openalex.org/W3200135021","https://openalex.org/W4287887917","https://openalex.org/W4385823311","https://openalex.org/W4387446848","https://openalex.org/W4389520025","https://openalex.org/W6679992976","https://openalex.org/W6755207826","https://openalex.org/W6763701032","https://openalex.org/W6810007534","https://openalex.org/W6846807982","https://openalex.org/W6859908464"],"related_works":["https://openalex.org/W4205899436","https://openalex.org/W2462138927","https://openalex.org/W3111427900","https://openalex.org/W4380355808","https://openalex.org/W2558617677","https://openalex.org/W2342456189","https://openalex.org/W2972445698","https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W4394972288"],"abstract_inverted_index":{"With":[0],"the":[1,8,63,67,79,106],"widespread":[2],"adoption":[3],"of":[4,11,17,28,123,128,133],"internet":[5],"technology":[6],"and":[7,44,66,78,130,137],"rapid":[9],"development":[10],"information":[12,48,59,92],"technology,":[13],"an":[14,125,131],"increasing":[15],"number":[16],"viewpoints":[18,30],"are":[19,70,103],"being":[20],"conveyed":[21,36],"on":[22,105,142],"online":[23],"platforms,":[24],"making":[25],"emotion":[26,54,117],"recognition":[27,118],"these":[29,50],"very":[31],"important.":[32],"Information":[33],"is":[34,82],"typically":[35],"in":[37,100],"multimodal":[38,116],"forms,":[39],"such":[40],"as":[41],"text,":[42],"audio,":[43],"video":[45],"modalities.":[46],"Combining":[47],"from":[49,60,93],"modalities":[51],"can":[52,139],"enhance":[53],"recognition.":[55],"This":[56],"study":[57],"integrates":[58],"two":[61],"modalities:":[62],"BERT":[64],"model":[65,69,81],"RoBERTa":[68],"introduced":[71,83],"for":[72,84,96],"text":[73],"modality":[74,86],"to":[75,87],"extract":[76,88],"features,":[77,89],"data2vec2.0":[80],"audio":[85],"incorporating":[90],"contextual":[91],"previous":[94],"dialogues":[95],"training.":[97],"All":[98],"experiments":[99],"this":[101],"paper":[102],"conducted":[104],"IEMOCAP":[107],"dataset,":[108],"using":[109],"a":[110,120],"five-fold":[111],"cross-validation":[112],"method.":[113],"The":[114,135],"final":[115],"achieves":[119],"weighted":[121],"accuracy":[122,127],"78.49%,":[124],"unweighted":[126],"79.38%,":[129],"F1-score":[132],"78.43%.":[134],"models":[136],"code":[138],"be":[140],"found":[141],"https://github.com/xiazhengshun/multimodal-emotion-recognition.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}