{"id":"https://openalex.org/W4388103902","doi":"https://doi.org/10.1109/aibthings58340.2023.10292462","title":"Automatic Recognition of Emotions in Speech With Large Self-Supervised Learning Transformer Models","display_name":"Automatic Recognition of Emotions in Speech With Large Self-Supervised Learning Transformer Models","publication_year":2023,"publication_date":"2023-09-16","ids":{"openalex":"https://openalex.org/W4388103902","doi":"https://doi.org/10.1109/aibthings58340.2023.10292462"},"language":"en","primary_location":{"id":"doi:10.1109/aibthings58340.2023.10292462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aibthings58340.2023.10292462","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 Artificial Intelligence, Blockchain, and Internet of Things (AIBThings)","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":"Mrunal Prakash Gavali","orcid":null},"institutions":[{"id":"https://openalex.org/I157638225","display_name":"California State University, Northridge","ror":"https://ror.org/005f5hv41","country_code":"US","type":"education","lineage":["https://openalex.org/I157638225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mrunal Prakash Gavali","raw_affiliation_strings":["California State University, Northridge,Department of Computer Science,Northridge,CA,USA","Department of Computer Science, California State University, Northridge, Northridge, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California State University, Northridge,Department of Computer Science,Northridge,CA,USA","institution_ids":["https://openalex.org/I157638225"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Northridge, Northridge, CA, USA","institution_ids":["https://openalex.org/I157638225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086227422","display_name":"Abhishek Verma","orcid":"https://orcid.org/0000-0001-6687-4809"},"institutions":[{"id":"https://openalex.org/I157638225","display_name":"California State University, Northridge","ror":"https://ror.org/005f5hv41","country_code":"US","type":"education","lineage":["https://openalex.org/I157638225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Verma","raw_affiliation_strings":["California State University, Northridge,Department of Computer Science,Northridge,CA,USA","Department of Computer Science, California State University, Northridge, Northridge, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California State University, Northridge,Department of Computer Science,Northridge,CA,USA","institution_ids":["https://openalex.org/I157638225"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Northridge, Northridge, CA, USA","institution_ids":["https://openalex.org/I157638225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157638225"],"apc_list":null,"apc_paid":null,"fwci":1.6282,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84329415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.776877760887146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5739132761955261},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.5338420271873474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46833205223083496},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4244394898414612},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41780608892440796},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3843943476676941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.776877760887146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5739132761955261},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.5338420271873474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46833205223083496},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4244394898414612},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41780608892440796},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3843943476676941},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aibthings58340.2023.10292462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aibthings58340.2023.10292462","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 Artificial Intelligence, Blockchain, and Internet of Things (AIBThings)","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/W2101234009","https://openalex.org/W2803193013","https://openalex.org/W2896457183","https://openalex.org/W2979826702","https://openalex.org/W3094550259","https://openalex.org/W3160525311","https://openalex.org/W3170774791","https://openalex.org/W3197580070","https://openalex.org/W3197876970","https://openalex.org/W3208743843","https://openalex.org/W3213879871","https://openalex.org/W4205633160","https://openalex.org/W4225635674","https://openalex.org/W4295312788","https://openalex.org/W4312951904","https://openalex.org/W6675354045","https://openalex.org/W6755207826","https://openalex.org/W6766978945","https://openalex.org/W6802609832"],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W3200958703","https://openalex.org/W1990078780","https://openalex.org/W3108667266","https://openalex.org/W2376619307","https://openalex.org/W3118437876","https://openalex.org/W1527444722"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3,147],"is":[4,104,126],"an":[5],"important":[6],"area":[7],"of":[8,13,60,68,115,118,123,142,154,174,192],"research":[9,40,46,125],"in":[10,38,53,74,107],"the":[11,35,50,54,65,108,121,140,149,155,161,190,193],"realm":[12],"collaborative":[14],"and":[15,25,57,129,182],"social":[16],"robotics,":[17],"which":[18],"aims":[19],"to":[20,49,111,127,189],"enhance":[21],"human-robot":[22],"interaction":[23],"(HRI)":[24],"serves":[26],"as":[27,84],"a":[28,44,90,177],"feedback":[29],"mechanism":[30],"for":[31,89,93,139],"affective":[32],"computing.":[33],"Despite":[34],"recent":[36],"progress":[37],"SER":[39],"area,":[41],"it":[42,85],"remains":[43],"challenging":[45,150],"problem":[47,114],"due":[48],"profound":[51],"variations":[52],"complexity,":[55],"subjectivity,":[56],"contextual":[58],"heterogeneity":[59],"human":[61],"emotional":[62,71],"expressions.":[63],"Consequently,":[64],"inherent":[66],"difficulties":[67],"modeling":[69],"paralinguistic":[70],"information":[72],"embedded":[73],"speech":[75,109,144],"signals":[76],"are":[77,164],"further":[78],"compounded":[79],"when":[80],"employing":[81],"supervised":[82],"learning,":[83],"necessitates":[86],"annotated":[87,119],"labels":[88],"large-scale":[91],"dataset":[92,163],"satisfactory":[94],"model":[95,170,184],"performance.":[96],"To":[97],"this":[98,113],"end,":[99],"self-supervised":[100,135],"learning":[101,136],"(SSL)":[102,137],"approach":[103],"widely":[105],"adopted":[106],"domain":[110],"addresses":[112],"limited":[116],"availability":[117],"data.Therefore,":[120],"focus":[122],"our":[124],"investigate":[128],"evaluate":[130],"several":[131],"state-of-the-art":[132],"large":[133,157,169],"attention-based":[134],"models":[138,159],"task":[141],"automatic":[143],"emotion":[145],"recognition":[146],"on":[148,160,186],"RAVDESS":[151,162],"dataset.":[152],"Results":[153],"four":[156],"SSL":[158],"promising.":[165],"In":[166],"particular":[167],"HuBERT":[168],"achieved":[171],"highest":[172],"accuracy":[173],"88%":[175],"with":[176],"much":[178],"lower":[179,183],"training":[180],"time":[181],"size":[185],"disk":[187],"compared":[188],"rest":[191],"models.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}