{"id":"https://openalex.org/W4391307921","doi":"https://doi.org/10.1109/smc53992.2023.10394418","title":"Multimodal Speech Emotion Recognition Using Modality-Specific Self-Supervised Frameworks","display_name":"Multimodal Speech Emotion Recognition Using Modality-Specific Self-Supervised Frameworks","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4391307921","doi":"https://doi.org/10.1109/smc53992.2023.10394418"},"language":"en","primary_location":{"id":"doi:10.1109/smc53992.2023.10394418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53992.2023.10394418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5076251331","display_name":"Rutherford Agbeshi Patamia","orcid":"https://orcid.org/0000-0002-6397-0974"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rutherford Agbeshi Patamia","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China,Chengdu,SC,China,610054"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China,Chengdu,SC,China,610054","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001663435","display_name":"Paulo E. Santos","orcid":"https://orcid.org/0000-0001-8484-0354"},"institutions":[{"id":"https://openalex.org/I169541294","display_name":"Flinders University","ror":"https://ror.org/01kpzv902","country_code":"AU","type":"education","lineage":["https://openalex.org/I169541294"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Paulo E. Santos","raw_affiliation_strings":["Flinders University,Centre for Defence Engineering, Research and Training College of Science Engineering,Tonsley,SA,Australia,5042"],"affiliations":[{"raw_affiliation_string":"Flinders University,Centre for Defence Engineering, Research and Training College of Science Engineering,Tonsley,SA,Australia,5042","institution_ids":["https://openalex.org/I169541294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089506484","display_name":"Kingsley Nketia Acheampong","orcid":"https://orcid.org/0000-0002-5593-4025"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kingsley Nketia Acheampong","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China,Chengdu,SC,China,610054"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China,Chengdu,SC,China,610054","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031026143","display_name":"Favour Ekong","orcid":"https://orcid.org/0000-0003-4986-4953"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Favour Ekong","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China,Chengdu,SC,China,610054"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China,Chengdu,SC,China,610054","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026135262","display_name":"Kwabena Sarpong","orcid":"https://orcid.org/0000-0002-2771-7074"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kwabena Sarpong","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China,Chengdu,SC,China,610054"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China,Chengdu,SC,China,610054","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":null,"display_name":"She Kun","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"She Kun","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China,Chengdu,SC,China,610054"],"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China,Chengdu,SC,China,610054","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076251331"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":2.4906,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89683334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4134","last_page":"4141"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9918000102043152,"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/T10860","display_name":"Speech and Audio Processing","score":0.9908999800682068,"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/computer-science","display_name":"Computer science","score":0.7544347047805786},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6962304711341858},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5903906226158142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5789852738380432},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.5214742422103882},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5213152766227722},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4873843789100647},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44400322437286377},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.43623220920562744},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.4354923665523529},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.40074342489242554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3926047086715698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544347047805786},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6962304711341858},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5903906226158142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5789852738380432},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.5214742422103882},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5213152766227722},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4873843789100647},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44400322437286377},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.43623220920562744},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.4354923665523529},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.40074342489242554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3926047086715698},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53992.2023.10394418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53992.2023.10394418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":33,"referenced_works":["https://openalex.org/W2076063813","https://openalex.org/W2127141656","https://openalex.org/W2146334809","https://openalex.org/W2803193013","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2919115771","https://openalex.org/W2963686995","https://openalex.org/W2971275122","https://openalex.org/W3014475539","https://openalex.org/W3015953902","https://openalex.org/W3022013598","https://openalex.org/W3036601975","https://openalex.org/W3091486761","https://openalex.org/W3094805191","https://openalex.org/W3095251683","https://openalex.org/W3096136448","https://openalex.org/W3096690837","https://openalex.org/W3096963953","https://openalex.org/W3161428216","https://openalex.org/W3192005042","https://openalex.org/W3196937856","https://openalex.org/W3197642003","https://openalex.org/W3206192140","https://openalex.org/W3215440557","https://openalex.org/W4200367851","https://openalex.org/W4200591749","https://openalex.org/W4281620477","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6802546489"],"related_works":["https://openalex.org/W3080495370","https://openalex.org/W4285597148","https://openalex.org/W4381827277","https://openalex.org/W3157841754","https://openalex.org/W4390136517","https://openalex.org/W2901531394","https://openalex.org/W4321599321","https://openalex.org/W1559262936","https://openalex.org/W2134707158","https://openalex.org/W2894458059"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,37,58,117],"is":[2,53,63],"a":[3],"topic":[4],"of":[5,109,158],"significant":[6],"interest":[7],"in":[8,29,56,122],"assistive":[9],"robotics":[10],"due":[11],"to":[12,15,21,90,95,138],"the":[13,19,149],"need":[14],"equip":[16],"robots":[17],"with":[18],"ability":[20],"comprehend":[22],"human":[23],"behavior,":[24],"facilitating":[25],"their":[26],"effective":[27],"interaction":[28],"our":[30],"society.":[31],"Consequently,":[32],"efficient":[33],"and":[34,51,70,111],"dependable":[35],"emotion":[36,57,82,116,142],"systems":[38],"supporting":[39],"optimal":[40],"human-machine":[41],"communication":[42],"are":[43,84],"required.":[44],"Multi-modality":[45],"(including":[46],"speech,":[47],"audio,":[48],"text,":[49],"images,":[50],"videos)":[52],"typically":[54],"exploited":[55],"tasks.":[59],"Much":[60],"relevant":[61],"research":[62],"based":[64],"on":[65],"merging":[66],"multiple":[67],"data":[68,77,133],"modalities":[69],"training":[71],"deep":[72],"learning":[73,93,108],"models":[74],"utilizing":[75],"low-level":[76],"representations.":[78,98],"However,":[79],"most":[80],"existing":[81],"databases":[83],"not":[85],"large":[86],"(or":[87],"complex)":[88],"enough":[89],"allow":[91],"machine":[92],"approaches":[94,165],"learn":[96],"detailed":[97],"This":[99,125],"paper":[100],"explores":[101],"modality-specific":[102],"pre-trained":[103],"transformer":[104],"frameworks":[105],"for":[106,114,160],"self-supervised":[107],"speech":[110,141],"text":[112],"representations":[113],"data-efficient":[115],"while":[118],"achieving":[119,154],"state-of-the-art":[120,164],"performance":[121],"recognizing":[123],"emotions.":[124],"model":[126,145],"applies":[127],"feature-level":[128],"fusion":[129],"using":[130,148],"nonverbal":[131],"cue":[132],"points":[134],"from":[135],"motion":[136],"capture":[137],"provide":[139],"multimodal":[140],"recognition.":[143],"The":[144],"was":[146],"trained":[147],"publicly":[150],"available":[151],"IEMOCAP":[152],"dataset,":[153],"an":[155],"overall":[156],"accuracy":[157],"77.58%":[159],"four":[161],"emotions,":[162],"outperforming":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}