{"id":"https://openalex.org/W4406137817","doi":"https://doi.org/10.1109/taffc.2025.3526592","title":"Multitask Transformer for Cross-Corpus Speech Emotion Recognition","display_name":"Multitask Transformer for Cross-Corpus Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-01-07","ids":{"openalex":"https://openalex.org/W4406137817","doi":"https://doi.org/10.1109/taffc.2025.3526592"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2025.3526592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3526592","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/A5051934007","display_name":"Chung-Soo Ahn","orcid":"https://orcid.org/0000-0001-6043-9523"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chung-Soo Ahn","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University (NTU), Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6043-9523","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080929578","display_name":"Rajib Rana","orcid":"https://orcid.org/0000-0002-0506-2409"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rajib Rana","raw_affiliation_strings":["University of Southern Queensland (USQ), Toowoomba, QLD, Australia","University of Southern Queensland, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0506-2409","affiliations":[{"raw_affiliation_string":"University of Southern Queensland (USQ), Toowoomba, QLD, Australia","institution_ids":["https://openalex.org/I185523456"]},{"raw_affiliation_string":"University of Southern Queensland, Australia","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"middle","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","Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA"],"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"]},{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026076885","display_name":"Jagath C. Rajapakse","orcid":"https://orcid.org/0000-0001-7944-1658"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jagath C. Rajapakse","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University (NTU), Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7944-1658","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.9399,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.99264516,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"16","issue":"3","first_page":"1581","last_page":"1591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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":0.9952999949455261,"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/T11309","display_name":"Music and Audio Processing","score":0.9926000237464905,"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":0.7862933874130249},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.7288945317268372},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.650896430015564},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6073040962219238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5215932130813599},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4935864210128784},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4808507561683655},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44618573784828186},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4395561218261719},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4347493052482605},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.28894221782684326},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0868467390537262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7862933874130249},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.7288945317268372},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.650896430015564},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6073040962219238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5215932130813599},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4935864210128784},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4808507561683655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44618573784828186},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4395561218261719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4347493052482605},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.28894221782684326},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0868467390537262},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2025.3526592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3526592","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W175750906","https://openalex.org/W1566289585","https://openalex.org/W1821462560","https://openalex.org/W2125462608","https://openalex.org/W2146334809","https://openalex.org/W2342475039","https://openalex.org/W2593116425","https://openalex.org/W2742542661","https://openalex.org/W2803098682","https://openalex.org/W2924116307","https://openalex.org/W2936451900","https://openalex.org/W2963447013","https://openalex.org/W2964128364","https://openalex.org/W2972724712","https://openalex.org/W2972906894","https://openalex.org/W2973034847","https://openalex.org/W2985076077","https://openalex.org/W2995813704","https://openalex.org/W3008554267","https://openalex.org/W3015141382","https://openalex.org/W3039591610","https://openalex.org/W3086923691","https://openalex.org/W3096615741","https://openalex.org/W3098994423","https://openalex.org/W3161933272","https://openalex.org/W3166157623","https://openalex.org/W3186351311","https://openalex.org/W3196974791","https://openalex.org/W3197580070","https://openalex.org/W3214882941","https://openalex.org/W3216440558","https://openalex.org/W4210528011","https://openalex.org/W4225302953","https://openalex.org/W4225694800","https://openalex.org/W4225959162","https://openalex.org/W4293691212","https://openalex.org/W4297841602","https://openalex.org/W4312119444","https://openalex.org/W4312327819","https://openalex.org/W4327852215","https://openalex.org/W4361994820","https://openalex.org/W4372267150","https://openalex.org/W4372267458","https://openalex.org/W4372267501","https://openalex.org/W4382722605","https://openalex.org/W4392903309","https://openalex.org/W4400975545","https://openalex.org/W4402111759"],"related_works":["https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W2821676139","https://openalex.org/W4287635093","https://openalex.org/W3043695725","https://openalex.org/W4382138864","https://openalex.org/W4387770285","https://openalex.org/W3022215768","https://openalex.org/W3135975972"],"abstract_inverted_index":{"Deep":[0],"learning":[1,85],"has":[2],"significantly":[3],"advanced":[4],"the":[5,28,54,56,80,94,100,112,154,181,190,193,200],"field":[6],"of":[7,30,111,117,192],"Speech":[8],"Emotion":[9],"Recognition":[10],"(SER),":[11],"yet":[12],"its":[13],"efficacy":[14],"in":[15,130,203],"cross-corpus":[16,60,135,143,204],"scenarios":[17,136],"remains":[18],"a":[19,74,108,122],"challenge.":[20],"To":[21,69],"overcome":[22],"this":[23],"limitation,":[24],"recent":[25],"studies":[26],"demonstrate":[27,189],"success":[29],"multitask":[31,75,119,159],"learning,":[32],"which":[33],"uses":[34],"auxiliary":[35,90,95],"tasks":[36,96],"to":[37,50,98,106,134],"reduce":[38],"difference":[39],"between":[40],"source":[41,49],"and":[42,66,83,86,163,165,175,184],"target":[43,51,101,113],"dataset":[44],"(or":[45],"transfer":[46],"knowledge":[47],"from":[48],"datasets).":[52],"Despite":[53],"efforts,":[55],"overall":[57],"accuracy":[58],"for":[59,142,161],"SER":[61,78],"is":[62,121,137,145],"still":[63,138],"relatively":[64],"low":[65],"needs":[67],"attention.":[68],"improve":[70],"performance,":[71],"we":[72],"propose":[73],"framework":[76,120],"with":[77],"as":[79,89,148,153],"primary":[81],"task":[82],"contrastive":[84],"information":[87],"maximization":[88],"tasks.":[91],"We":[92,150,171],"design":[93],"innovatively":[97],"use":[99,151,172],"data":[102],"without":[103],"emotional":[104],"labels":[105],"develop":[107],"better":[109],"understanding":[110],"data.":[114],"The":[115,187],"core":[116],"our":[118],"pre-trained":[123],"transformer.":[124],"While":[125],"transformers":[126,160],"have":[127],"gained":[128],"attention":[129],"SER,":[131],"their":[132],"application":[133],"limited.":[139],"Multimodal":[140],"approaches":[141],"scenario":[144],"substantially":[146],"limited":[147],"well.":[149],"text":[152,164],"second":[155],"modality,":[156],"developing":[157],"separate":[158],"audio":[162],"conduct":[166],"decision-level":[167],"fusion":[168],"during":[169],"inference.":[170],"publicly":[173],"available":[174],"widely":[176],"used":[177],"speech":[178],"corpora,":[179],"including":[180],"IEMOCAP,":[182],"MSP-IMPROV":[183],"EMO-DB":[185],"databases.":[186],"results":[188],"benefits":[191],"proposed":[194],"approach,":[195],"achieving":[196],"improved":[197],"performance":[198],"on":[199],"benchmark":[201],"databases":[202],"settings.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}