{"id":"https://openalex.org/W4408859592","doi":"https://doi.org/10.1109/lra.2025.3554949","title":"Personalized Speech Emotion Recognition in Human-Robot Interaction Using Vision Transformers","display_name":"Personalized Speech Emotion Recognition in Human-Robot Interaction Using Vision Transformers","publication_year":2025,"publication_date":"2025-03-27","ids":{"openalex":"https://openalex.org/W4408859592","doi":"https://doi.org/10.1109/lra.2025.3554949"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3554949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3554949","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Robotics and Automation Letters","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/A5061583079","display_name":"Ruchik Mishra","orcid":"https://orcid.org/0000-0001-9453-7375"},"institutions":[{"id":"https://openalex.org/I142740786","display_name":"University of Louisville","ror":"https://ror.org/01ckdn478","country_code":"US","type":"education","lineage":["https://openalex.org/I142740786"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ruchik Mishra","raw_affiliation_strings":["Louisville Automation and Robotics Research Institute, University of Louisville, Louisville, KY, USA","Louisville Automation and Robotics Research Institute (LARRI), University of Louisville, KY, USA"],"raw_orcid":"https://orcid.org/0000-0001-9453-7375","affiliations":[{"raw_affiliation_string":"Louisville Automation and Robotics Research Institute, University of Louisville, Louisville, KY, USA","institution_ids":["https://openalex.org/I142740786","https://openalex.org/I4210116723"]},{"raw_affiliation_string":"Louisville Automation and Robotics Research Institute (LARRI), University of Louisville, KY, USA","institution_ids":["https://openalex.org/I142740786","https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114387261","display_name":"Andrew Frye","orcid":null},"institutions":[{"id":"https://openalex.org/I142740786","display_name":"University of Louisville","ror":"https://ror.org/01ckdn478","country_code":"US","type":"education","lineage":["https://openalex.org/I142740786"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Frye","raw_affiliation_strings":["Louisville Automation and Robotics Research Institute, University of Louisville, Louisville, KY, USA","Louisville Automation and Robotics Research Institute (LARRI), University of Louisville, KY, USA"],"raw_orcid":"https://orcid.org/0009-0009-9222-9892","affiliations":[{"raw_affiliation_string":"Louisville Automation and Robotics Research Institute, University of Louisville, Louisville, KY, USA","institution_ids":["https://openalex.org/I142740786","https://openalex.org/I4210116723"]},{"raw_affiliation_string":"Louisville Automation and Robotics Research Institute (LARRI), University of Louisville, KY, USA","institution_ids":["https://openalex.org/I142740786","https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090036593","display_name":"Madan M. Rayguru","orcid":null},"institutions":[{"id":"https://openalex.org/I142740786","display_name":"University of Louisville","ror":"https://ror.org/01ckdn478","country_code":"US","type":"education","lineage":["https://openalex.org/I142740786"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madan M. Rayguru","raw_affiliation_strings":["Louisville Automation and Robotics Research Institute, University of Louisville, Louisville, KY, USA","Louisville Automation and Robotics Research Institute (LARRI), University of Louisville, KY, USA"],"raw_orcid":"https://orcid.org/0000-0003-4339-4444","affiliations":[{"raw_affiliation_string":"Louisville Automation and Robotics Research Institute, University of Louisville, Louisville, KY, USA","institution_ids":["https://openalex.org/I142740786","https://openalex.org/I4210116723"]},{"raw_affiliation_string":"Louisville Automation and Robotics Research Institute (LARRI), University of Louisville, KY, USA","institution_ids":["https://openalex.org/I142740786","https://openalex.org/I4210116723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089902968","display_name":"Dan O. Popa","orcid":"https://orcid.org/0000-0002-2360-0020"},"institutions":[{"id":"https://openalex.org/I142740786","display_name":"University of Louisville","ror":"https://ror.org/01ckdn478","country_code":"US","type":"education","lineage":["https://openalex.org/I142740786"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan O. Popa","raw_affiliation_strings":["Louisville Automation and Robotics Research Institute, University of Louisville, Louisville, KY, USA","Louisville Automation and Robotics Research Institute (LARRI), University of Louisville, KY, USA"],"raw_orcid":"https://orcid.org/0000-0002-2360-0020","affiliations":[{"raw_affiliation_string":"Louisville Automation and Robotics Research Institute, University of Louisville, Louisville, KY, USA","institution_ids":["https://openalex.org/I142740786","https://openalex.org/I4210116723"]},{"raw_affiliation_string":"Louisville Automation and Robotics Research Institute (LARRI), University of Louisville, KY, USA","institution_ids":["https://openalex.org/I142740786","https://openalex.org/I4210116723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061583079"],"corresponding_institution_ids":["https://openalex.org/I142740786","https://openalex.org/I4210116723"],"apc_list":null,"apc_paid":null,"fwci":4.3293,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9370187,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"10","issue":"5","first_page":"4890","last_page":"4897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.8066999912261963,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.8066999912261963,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12222","display_name":"IoT-based Smart Home Systems","score":0.8062000274658203,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.755299985408783,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.6436758041381836},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6063222885131836},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5162546634674072},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5000324249267578},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.478975772857666},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.43630537390708923},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4269223213195801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3899450898170471},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38171035051345825},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.32115429639816284},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2374945878982544},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06749531626701355}],"concepts":[{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.6436758041381836},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6063222885131836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5162546634674072},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5000324249267578},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.478975772857666},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.43630537390708923},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4269223213195801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3899450898170471},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38171035051345825},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32115429639816284},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2374945878982544},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06749531626701355},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3554949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3554949","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2530352066","display_name":null,"funder_award_id":"1849213","funder_id":"https://openalex.org/F4320338283","funder_display_name":"Office of Experimental Program to Stimulate Competitive Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320338283","display_name":"Office of Experimental Program to Stimulate Competitive Research","ror":"https://ror.org/04k9mqs78"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1963552095","https://openalex.org/W2016433830","https://openalex.org/W2030931454","https://openalex.org/W2137129454","https://openalex.org/W2295001676","https://openalex.org/W2312140198","https://openalex.org/W2408520939","https://openalex.org/W2747664154","https://openalex.org/W2963686995","https://openalex.org/W2963914279","https://openalex.org/W2972273766","https://openalex.org/W3007721991","https://openalex.org/W3081192838","https://openalex.org/W3101745004","https://openalex.org/W3136897485","https://openalex.org/W3145643603","https://openalex.org/W3163573274","https://openalex.org/W3187638037","https://openalex.org/W3197642003","https://openalex.org/W3198908807","https://openalex.org/W3210797221","https://openalex.org/W4205633160","https://openalex.org/W4226162428","https://openalex.org/W4296068596","https://openalex.org/W4312292725","https://openalex.org/W4313178214","https://openalex.org/W4362650882","https://openalex.org/W4375854028","https://openalex.org/W4385876305","https://openalex.org/W4387261468","https://openalex.org/W4390905786","https://openalex.org/W4391407069","https://openalex.org/W4391987579","https://openalex.org/W4392172995","https://openalex.org/W4399434529","https://openalex.org/W4401609030","https://openalex.org/W4402111427","https://openalex.org/W4402112352","https://openalex.org/W4405809056"],"related_works":["https://openalex.org/W8302103","https://openalex.org/W3171631314","https://openalex.org/W2674584172","https://openalex.org/W4287179229","https://openalex.org/W3205513966","https://openalex.org/W3126677997","https://openalex.org/W3120459843","https://openalex.org/W1610857240","https://openalex.org/W4366547574","https://openalex.org/W3200191727"],"abstract_inverted_index":{"Emotions":[0],"are":[1],"an":[2],"essential":[3],"element":[4],"in":[5,50,113,150],"human":[6,84],"verbal":[7],"communication,":[8],"therefore":[9],"it":[10],"is":[11,54],"important":[12],"to":[13,55,115],"understand":[14],"individuals'":[15],"affect":[16],"during":[17],"human-robot":[18],"interaction":[19],"(HRI).":[20],"This":[21],"letter":[22],"investigates":[23],"the":[24,57,90,111],"application":[25],"of":[26,41],"vision":[27,132],"transformer":[28],"models,":[29],"namely":[30],"ViT":[31,98],"(Vision":[32],"Transformers)":[33,43],"and":[34,71,99,102,125,137],"BEiT":[35],"(Bidirectional":[36],"Encoder":[37],"Representations":[38],"from":[39,82,110,120],"Pre-Training":[40],"Image":[42],"pipelines":[44],"for":[45,60],"Speech":[46],"Emotion":[47],"Recognition":[48],"(SER)":[49],"HRI.":[51],"The":[52,127],"focus":[53],"generalize":[56],"SER":[58],"models":[59,67,101,105,144,148],"individual":[61],"speech":[62,108],"characteristics":[63],"by":[64],"fine-tuning":[65,131,155],"these":[66,104,141],"on":[68,106,134],"benchmark":[69,135],"datasets":[70,136],"exploiting":[72],"ensemble":[73],"methods.":[74],"For":[75],"this":[76],"purpose,":[77],"we":[78],"collected":[79],"audio":[80],"data":[81],"several":[83],"subjects":[85],"having":[86],"pseudo-naturalistic":[87],"conversations":[88],"with":[89],"NAO":[91],"social":[92],"robot.":[93],"We":[94],"then":[95,138],"fine-tuned":[96,143],"our":[97],"BEiT-based":[100],"tested":[103],"unseen":[107],"samples":[109],"participants":[112],"order":[114],"dentify":[116],"four":[117],"primary":[118],"emotions":[119],"speech:":[121],"neutral,":[122],"happy,":[123],"sad,":[124],"angry.":[126],"results":[128,149],"show":[129],"that":[130],"transformers":[133],"using":[139],"either":[140],"already":[142],"or":[145,157],"ensembling":[146],"ViT/BEiT":[147],"higher":[151],"classification":[152],"accuracies":[153],"than":[154],"vanilla-ViTs":[156],"BEiTs.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-01T08:36:08.643496","created_date":"2025-10-10T00:00:00"}
