{"id":"https://openalex.org/W4398176306","doi":"https://doi.org/10.1080/08839514.2024.2356992","title":"Bi-Modal Bi-Task Emotion Recognition Based on Transformer Architecture","display_name":"Bi-Modal Bi-Task Emotion Recognition Based on Transformer Architecture","publication_year":2024,"publication_date":"2024-05-21","ids":{"openalex":"https://openalex.org/W4398176306","doi":"https://doi.org/10.1080/08839514.2024.2356992"},"language":"en","primary_location":{"id":"doi:10.1080/08839514.2024.2356992","is_oa":true,"landing_page_url":"https://doi.org/10.1080/08839514.2024.2356992","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/08839514.2024.2356992?needAccess=true","source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.tandfonline.com/doi/pdf/10.1080/08839514.2024.2356992?needAccess=true","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013078277","display_name":"Yu Song","orcid":"https://orcid.org/0009-0001-2078-8793"},"institutions":[{"id":"https://openalex.org/I4210102701","display_name":"Jilin Vocational College of Industry and Technology","ror":"https://ror.org/017s6v868","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210102701"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Song","raw_affiliation_strings":["School of Energy Engineering, Jiangxi Vocational College of Industry & Engineering, Pingxiang, Jiangxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Energy Engineering, Jiangxi Vocational College of Industry & Engineering, Pingxiang, Jiangxi, China","institution_ids":["https://openalex.org/I4210102701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111863438","display_name":"Qi Zhou","orcid":"https://orcid.org/0000-0001-8353-7062"},"institutions":[{"id":"https://openalex.org/I4210151260","display_name":"Guangdong Open University","ror":"https://ror.org/054fysp39","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151260"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Zhou","raw_affiliation_strings":["School of Artificial Intelligence, Guangdong Open University, Guangzhou, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Guangdong Open University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I4210151260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111863438"],"corresponding_institution_ids":["https://openalex.org/I4210151260"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":{"value":2195,"currency":"USD","value_usd":2195},"fwci":2.319,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87980161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"38","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9984999895095825,"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":0.9984999895095825,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9776999950408936,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8773713707923889},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7561177015304565},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7368463277816772},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6823409795761108},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6350427269935608},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4997744560241699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37349170446395874},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36257898807525635},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.20235618948936462},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1050424873828888},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06825882196426392}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8773713707923889},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7561177015304565},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7368463277816772},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6823409795761108},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6350427269935608},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4997744560241699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37349170446395874},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36257898807525635},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.20235618948936462},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1050424873828888},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06825882196426392},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/08839514.2024.2356992","is_oa":true,"landing_page_url":"https://doi.org/10.1080/08839514.2024.2356992","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/08839514.2024.2356992?needAccess=true","source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6a70601b6f8a42908c15a7d50cc0abd9","is_oa":false,"landing_page_url":"https://doaj.org/article/6a70601b6f8a42908c15a7d50cc0abd9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Applied Artificial Intelligence, Vol 38, Iss 1 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1080/08839514.2024.2356992","is_oa":true,"landing_page_url":"https://doi.org/10.1080/08839514.2024.2356992","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/08839514.2024.2356992?needAccess=true","source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4398176306.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W2777468850","https://openalex.org/W2905266130","https://openalex.org/W2964051877","https://openalex.org/W2970971581","https://openalex.org/W2972311718","https://openalex.org/W2973049979","https://openalex.org/W2973110385","https://openalex.org/W3015267357","https://openalex.org/W3015489952","https://openalex.org/W3016092640","https://openalex.org/W3022013598","https://openalex.org/W3096147072","https://openalex.org/W3107675414","https://openalex.org/W3120680448","https://openalex.org/W3136524425","https://openalex.org/W3170136709","https://openalex.org/W3183891373","https://openalex.org/W3186192207","https://openalex.org/W3193087369","https://openalex.org/W3193484423","https://openalex.org/W3197977579","https://openalex.org/W4206326349","https://openalex.org/W4225635674","https://openalex.org/W4280544120","https://openalex.org/W4283016277","https://openalex.org/W4288050061","https://openalex.org/W4295312788","https://openalex.org/W4309729109","https://openalex.org/W4309744786","https://openalex.org/W4312327819","https://openalex.org/W4312611743","https://openalex.org/W4312729513","https://openalex.org/W4315786723","https://openalex.org/W4321022102","https://openalex.org/W4321194918","https://openalex.org/W4321599321","https://openalex.org/W4322743615","https://openalex.org/W4327695709","https://openalex.org/W4367281761","https://openalex.org/W4382246105","https://openalex.org/W4382318707","https://openalex.org/W4385245566","https://openalex.org/W4385567987","https://openalex.org/W4387682244","https://openalex.org/W4392172995","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2588198209","https://openalex.org/W2320915480","https://openalex.org/W1909006023","https://openalex.org/W3200723557","https://openalex.org/W4205824991","https://openalex.org/W2362990116","https://openalex.org/W2381300099"],"abstract_inverted_index":{"In":[0],"the":[1,58,75,84,100,132,151,160,163],"field":[2],"of":[3,127],"emotion":[4,13,48],"recognition,":[5],"analyzing":[6],"emotions":[7],"from":[8,74,118],"speech":[9,12],"alone":[10],"(single-modal":[11],"recognition)":[14],"has":[15],"several":[16],"limitations,":[17],"including":[18],"limited":[19],"data":[20,76],"volume":[21],"and":[22,30,80,111,129,134,155],"low":[23],"accuracy.":[24,157],"Additionally,":[25],"single-task":[26],"models":[27],"lack":[28],"generalization":[29],"fail":[31],"to":[32,70,108,114,159],"fully":[33],"utilize":[34],"relevant":[35],"information.":[36,82],"To":[37],"address":[38],"these":[39],"issues,":[40],"this":[41],"paper":[42],"proposes":[43],"a":[44,104],"new":[45],"bi-modal":[46],"bi-task":[47],"recognition":[49],"model.":[50],"The":[51,121],"proposed":[52,101,122],"model":[53,87,102,123,152],"introduces":[54],"multi-task":[55],"learning":[56],"on":[57,131],"Transformer":[59],"architecture.":[60],"On":[61,83],"one":[62],"hand,":[63,86],"unsupervised":[64],"contrastive":[65,97],"predictive":[66],"coding":[67],"is":[68,92,145,165],"used":[69],"extract":[71],"denser":[72],"features":[73,117],"while":[77],"preserving":[78],"self-information":[79],"context-related":[81],"other":[85],"robustness":[88],"against":[89],"interfering":[90],"information":[91,113],"enhanced":[93],"by":[94],"employing":[95],"self-supervised":[96],"learning.":[98],"Furthermore,":[99],"utilizes":[103],"modality":[105],"fusion":[106],"module":[107],"incorporate":[109],"textual":[110],"audio":[112],"implicitly":[115],"align":[116],"both":[119],"modalities.":[120],"achieved":[124,153],"accuracy":[125,141,149],"rates":[126],"82.3%":[128],"83.5%":[130],"IEMOCAP":[133],"RAVDESS":[135],"datasets,":[136],"respectively,":[137],"when":[138],"considering":[139],"weighted":[140],"(WA).":[142],"When":[143],"weight":[144],"not":[146],"considered":[147],"(unweighted":[148],"(UA)),":[150],"83.0%":[154],"82.4%":[156],"Compared":[158],"existing":[161],"methods,":[162],"performance":[164],"further":[166],"improved.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}