{"id":"https://openalex.org/W4402363922","doi":"https://doi.org/10.14428/esann/2024.es2024-219","title":"Decision fusion based multimodal hierarchical method for speech emotion recognition from audio and text","display_name":"Decision fusion based multimodal hierarchical method for speech emotion recognition from audio and text","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402363922","doi":"https://doi.org/10.14428/esann/2024.es2024-219"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2024.es2024-219","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2024.es2024-219","pdf_url":"http://dx.doi.org/10.14428/esann/2024.es2024-219","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2024 proceesdings","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.14428/esann/2024.es2024-219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107083784","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 - UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cardiff University - School of computer Science and Informatics - UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432133","display_name":"Yuhua Li","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":"Yuhua Li","raw_affiliation_strings":["Cardiff University - School of computer Science and Informatics - UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cardiff University - School of computer Science and Informatics - UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","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 - UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cardiff University - School of computer Science and Informatics - UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031677311","display_name":"David Marshall","orcid":"https://orcid.org/0000-0003-2789-1395"},"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":"David marshall","raw_affiliation_strings":["Cardiff University - School of computer Science and Informatics - UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cardiff University - School of computer Science and Informatics - 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":1.4603,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8216022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"251","last_page":"256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.4620000123977661,"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":0.4620000123977661,"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":0.4131999909877777,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7557656764984131},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6899588108062744},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6557317972183228},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.49537742137908936},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.47034624218940735},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45947590470314026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4341166317462921},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4150680899620056},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.355001300573349},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.21593225002288818},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1652986705303192},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1412881314754486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557656764984131},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6899588108062744},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6557317972183228},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.49537742137908936},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.47034624218940735},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45947590470314026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4341166317462921},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4150680899620056},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.355001300573349},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.21593225002288818},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1652986705303192},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1412881314754486},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14428/esann/2024.es2024-219","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2024.es2024-219","pdf_url":"http://dx.doi.org/10.14428/esann/2024.es2024-219","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2024 proceesdings","raw_type":"proceedings-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:170045","is_oa":true,"landing_page_url":"https://orca.cardiff.ac.uk/view/cardiffauthors/A2475253J.html>,","pdf_url":"https://orca.cardiff.ac.uk/id/eprint/170045/1/ES2024-219-2.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.14428/esann/2024.es2024-219","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2024.es2024-219","pdf_url":"http://dx.doi.org/10.14428/esann/2024.es2024-219","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2024 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402363922.pdf","grobid_xml":"https://content.openalex.org/works/W4402363922.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W4243125559","https://openalex.org/W1541790149","https://openalex.org/W4241778367","https://openalex.org/W2752054555","https://openalex.org/W4312266741","https://openalex.org/W2527828870","https://openalex.org/W2184127972","https://openalex.org/W4214489098"],"abstract_inverted_index":{"Expressing":[0],"emotions":[1,9],"is":[2],"essential":[3],"in":[4,87],"human":[5],"interaction.Often,":[6],"individuals":[7],"convey":[8,23],"through":[10],"neutral":[11,26,69],"speech,":[12],"while":[13],"the":[14,75],"underlying":[15],"meaning":[16],"carries":[17],"emotional":[18,54,67],"weight.Conversely,":[19],"tone":[20],"can":[21],"also":[22],"emotion":[24,40],"despite":[25],"words.Most":[27],"Speech":[28],"Emotion":[29],"Recognition":[30],"research":[31],"overlooks":[32],"this.We":[33],"address":[34],"this":[35],"gap":[36],"with":[37],"a":[38,47],"multimodal":[39],"recognition":[41],"system":[42],"using":[43],"hierarchical":[44],"classifiers":[45],"and":[46,58,83,89],"novel":[48],"decision":[49],"fusion":[50],"method.Our":[51],"approach":[52],"analyses":[53],"cues":[55],"from":[56],"speech":[57],"text,":[59],"measuring":[60],"their":[61],"impact":[62],"on":[63,74],"predicted":[64],"classes,":[65],"considering":[66],"or":[68],"contributions":[70],"for":[71],"each":[72],"instance.Results":[73],"IEMOCAP":[76],"dataset":[77],"show":[78],"our":[79],"method's":[80],"effectiveness:":[81],"69.45%":[82],"65.26%":[84],"weighted":[85],"accuracy":[86],"speaker-dependent":[88],"speaker-independent":[90],"settings,":[91],"respectively.":[92]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
