{"id":"https://openalex.org/W4402352607","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650087","title":"Improving Speech Emotion Recognition through Hierarchical Classification and Text Integration for Enhanced Emotional Analysis and Contextual Understanding","display_name":"Improving Speech Emotion Recognition through Hierarchical Classification and Text Integration for Enhanced Emotional Analysis and Contextual Understanding","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352607","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650087"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650087","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5107079605","display_name":"Nawal Alqurashi","orcid":null},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nawal Alqurashi","raw_affiliation_strings":["Cardiff University,School of Computer Science and Informatics,Cardiff,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cardiff University,School of Computer Science and Informatics,Cardiff,UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432144","display_name":"Yuhua Li","orcid":"https://orcid.org/0000-0003-2913-4478"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuhua Li","raw_affiliation_strings":["Cardiff University,School of Computer Science and Informatics,Cardiff,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cardiff University,School of Computer Science and Informatics,Cardiff,UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103784688","display_name":"Kirill Sidorov","orcid":null},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kirill Sidorov","raw_affiliation_strings":["Cardiff University,School of Computer Science and Informatics,Cardiff,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cardiff University,School of Computer Science and Informatics,Cardiff,UK","institution_ids":["https://openalex.org/I79510175"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79510175"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20262267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"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/emotion-recognition","display_name":"Emotion recognition","score":0.7424252033233643},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6903249025344849},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5190101861953735},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4933530390262604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4021715223789215}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7424252033233643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6903249025344849},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5190101861953735},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4933530390262604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4021715223789215}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650087","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:168675","is_oa":false,"landing_page_url":"https://orca.cardiff.ac.uk/id/eprint/168675/1/m88551-alqurashi%20final-2.pdf","pdf_url":"https://orca.cardiff.ac.uk/id/eprint/168675/1/m88551-alqurashi%20final-2.pdf","source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1534131679","https://openalex.org/W2090777335","https://openalex.org/W2146334809","https://openalex.org/W2191779130","https://openalex.org/W2239141610","https://openalex.org/W2584561145","https://openalex.org/W2889169802","https://openalex.org/W2896457183","https://openalex.org/W2939224318","https://openalex.org/W2949676527","https://openalex.org/W2962770129","https://openalex.org/W2973110385","https://openalex.org/W3007348105","https://openalex.org/W3014475539","https://openalex.org/W3036601975","https://openalex.org/W3041730883","https://openalex.org/W3156669407","https://openalex.org/W3197642003","https://openalex.org/W3208480086","https://openalex.org/W3211224152","https://openalex.org/W4223944998","https://openalex.org/W4283016277","https://openalex.org/W4296523924","https://openalex.org/W4309568943","https://openalex.org/W4312209192","https://openalex.org/W4375869379","https://openalex.org/W4379230561","https://openalex.org/W4385655423","https://openalex.org/W4386826611","https://openalex.org/W6729014267"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,14],"recognition":[2,74],"(SER)":[3],"systems":[4],"are":[5],"designed":[6],"to":[7,36,45,93],"classify":[8],"spoken":[9,50],"audio":[10],"samples":[11,19,51],"into":[12],"different":[13],"categories.":[15],"However,":[16],"misclassifying":[17],"emotional":[18,54,98,111],"and":[20,71,85,130,143],"predicting":[21],"them":[22],"as":[23,56,89,127],"neutral":[24,49,115],"remains":[25],"a":[26,80,90],"challenging":[27],"problem":[28],"in":[29,76,109,113,123],"these":[30,57],"systems.":[31],"One":[32],"primary":[33],"contributing":[34],"factor":[35],"this":[37,69],"issue":[38,70],"is":[39],"the":[40,73,95],"limitation":[41],"of":[42,97],"speech":[43,136],"features":[44,58,88,101],"recognize":[46],"emotions":[47,134],"from":[48,135],"that":[52,106],"convey":[53],"context,":[55],"do":[59],"not":[60],"account":[61],"for":[62,140],"contextual":[63,104],"or":[64],"meaning-based":[65],"features.":[66],"To":[67],"address":[68,94],"improve":[72],"performance":[75],"SER,":[77],"we":[78],"propose":[79],"hierarchically":[81],"structured":[82],"classification":[83],"model":[84],"integrate":[86],"text":[87],"supportive":[91],"modality":[92],"misclassification":[96],"samples.":[99],"Text-based":[100],"provide":[102],"valuable":[103],"information":[105],"can":[107,137],"aid":[108],"identifying":[110],"content":[112],"otherwise":[114],"speech.":[116],"This":[117],"work":[118],"could":[119],"be":[120,138],"potentially":[121],"applied":[122],"various":[124],"fields,":[125],"such":[126],"healthcare,":[128],"education,":[129],"entertainment,":[131],"where":[132],"recognizing":[133],"crucial":[139],"effective":[141],"communication":[142],"decision-making.":[144]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}