{"id":"https://openalex.org/W7117116293","doi":"https://doi.org/10.1109/taffc.2025.3647876","title":"Harnessing Multimodal Unlabeled Data for Enhanced Speech Emotion Recognition","display_name":"Harnessing Multimodal Unlabeled Data for Enhanced Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-12-24","ids":{"openalex":"https://openalex.org/W7117116293","doi":"https://doi.org/10.1109/taffc.2025.3647876"},"language":null,"primary_location":{"id":"doi:10.1109/taffc.2025.3647876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3647876","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Transactions on Affective Computing","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/A5017966455","display_name":"Lucas Goncalves","orcid":"https://orcid.org/0000-0001-9613-1002"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lucas Goncalves","raw_affiliation_strings":["Erik Jonsson School of Engineering &#x0026; Computer Science, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-9613-1002","affiliations":[{"raw_affiliation_string":"Erik Jonsson School of Engineering &#x0026; Computer Science, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4075-4072","affiliations":[{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017966455"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67737462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"1","first_page":"1134","last_page":"1146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9905999898910522,"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":0.9905999898910522,"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":0.0012000000569969416,"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/T11448","display_name":"Face recognition and analysis","score":0.0012000000569969416,"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/facial-expression","display_name":"Facial expression","score":0.6568999886512756},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6425999999046326},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5633000135421753},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5267000198364258},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5260999798774719},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.4007999897003174},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.3792000114917755},{"id":"https://openalex.org/keywords/emotion-detection","display_name":"Emotion detection","score":0.3781000077724457},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3564000129699707}],"concepts":[{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.6568999886512756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6474000215530396},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6425999999046326},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5633000135421753},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5267000198364258},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5175999999046326},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4677000045776367},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3903000056743622},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.3781000077724457},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C2776141551","wikidata":"https://www.wikidata.org/wiki/Q16000087","display_name":"Emotion perception","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2025.3647876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3647876","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Transactions on Affective Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5692251324653625,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"<italic":[0,68,115],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[1,69,116],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Speech":[2],"emotion":[3,145],"recognition</i>":[4],"(SER)":[5],"often":[6],"faces":[7],"challenges":[8],"due":[9],"to":[10,26,58,66,83,168,175],"the":[11,38,113,195],"lack":[12],"of":[13,19,40,94,156],"large,":[14],"annotated":[15],"datasets.":[16],"The":[17],"presence":[18],"abundance":[20],"unlabeled":[21,54,157],"data":[22],"offers":[23],"a":[24,92,108,130,143],"chance":[25],"explore":[27],"methods":[28],"that":[29,202],"could":[30],"significantly":[31,205],"improve":[32],"SER":[33,180,207],"systems.":[34],"This":[35],"study":[36],"explores":[37],"feasibility":[39],"enhancing":[41],"general":[42],"speech":[43,172],"models":[44],"by":[45,142],"incorporating":[46],"unimodal":[47],"and":[48,136,198],"multimodal":[49,63,95,183],"training":[50],"objectives":[51,64,96,149],"derived":[52],"from":[53,87,101,129,153],"data,":[55],"specifically":[56],"tailored":[57],"extract":[59,84],"emotional":[60,85,158],"content.":[61],"These":[62,148],"aim":[65],"refine":[67],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">self-supervised":[70],"learning</i>":[71],"(SSL)-based":[72],"representations":[73,127],"that,":[74],"while":[75,185],"effective":[76],"in":[77,161,179,210],"SER,":[78],"were":[79],"not":[80],"originally":[81],"created":[82],"cues":[86],"speech.":[88],"Our":[89,191],"methodology":[90],"introduces":[91],"set":[93],"focused":[97],"on":[98,112],"capturing":[99],"information":[100],"three":[102],"primary":[103],"sources:":[104],"acoustic":[105],"signals,":[106],"through":[107,139],"representation":[109],"objective":[110],"based":[111],"extended":[114],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Geneva":[117],"Minimalistic":[118],"Acoustic":[119],"Parameter":[120],"Set</i>":[121],"(eGEMAPS);":[122],"facial":[123,132],"expressions,":[124],"via":[125],"visual":[126],"obtained":[128],"pre-trained":[131,144],"expression":[133],"recognition":[134],"system;":[135],"textual":[137],"content,":[138],"pseudo-labels":[140],"generated":[141,152],"sentiment":[146],"model.":[147],"are":[150],"automatically":[151],"70.7":[154],"hours":[155],"content":[159],"captured":[160],"naturalistic":[162],"settings.":[163],"We":[164],"apply":[165],"our":[166,203],"strategy":[167],"four":[169],"state-of-the-art":[170],"SSL-based":[171],"models,":[173],"aiming":[174],"enhance":[176],"their":[177],"capabilities":[178],"tasks":[181],"with":[182,212],"signals":[184],"still":[186],"keeping":[187],"inference":[188],"strictly":[189],"audio-only.":[190],"experimental":[192],"evaluations":[193],"across":[194],"CREMA-D,":[196],"MSP-IMPROV,":[197],"MSP-Podcast":[199],"datasets":[200],"demonstrate":[201],"approach":[204],"improves":[206],"performance,":[208],"especially":[209],"settings":[211],"limited":[213],"labeled":[214],"data.":[215]},"counts_by_year":[],"updated_date":"2026-03-03T06:13:14.889584","created_date":"2025-12-24T00:00:00"}