{"id":"https://openalex.org/W4312724610","doi":"https://doi.org/10.1109/ijcnn55064.2022.9891882","title":"A Comparison Between Convolutional and Transformer Architectures for Speech Emotion Recognition","display_name":"A Comparison Between Convolutional and Transformer Architectures for Speech Emotion Recognition","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312724610","doi":"https://doi.org/10.1109/ijcnn55064.2022.9891882"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9891882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9891882","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5069587466","display_name":"Shreyah Iyer","orcid":null},"institutions":[{"id":"https://openalex.org/I141584323","display_name":"University of Hertfordshire","ror":"https://ror.org/0267vjk41","country_code":"GB","type":"education","lineage":["https://openalex.org/I141584323"]},{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Shreyah Iyer","raw_affiliation_strings":["School of Physics,Engineering and Computer Science, University of Hertfordshire,Hatfield,UK","Intelligent Voice Ltd, London, UK","School of Physics,Engineering and Computer Science, University of Hertfordshire, Hatfield, UK"],"affiliations":[{"raw_affiliation_string":"School of Physics,Engineering and Computer Science, University of Hertfordshire,Hatfield,UK","institution_ids":["https://openalex.org/I141584323"]},{"raw_affiliation_string":"Intelligent Voice Ltd, London, UK","institution_ids":["https://openalex.org/I4210153682"]},{"raw_affiliation_string":"School of Physics,Engineering and Computer Science, University of Hertfordshire, Hatfield, UK","institution_ids":["https://openalex.org/I141584323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044554092","display_name":"Cornelius Glackin","orcid":"https://orcid.org/0000-0001-5114-6403"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cornelius Glackin","raw_affiliation_strings":["Intelligent Voice Ltd,London,UK","Intelligent Voice Ltd, London, UK"],"affiliations":[{"raw_affiliation_string":"Intelligent Voice Ltd,London,UK","institution_ids":["https://openalex.org/I4210153682"]},{"raw_affiliation_string":"Intelligent Voice Ltd, London, UK","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012466886","display_name":"Nigel Cannings","orcid":"https://orcid.org/0000-0002-5279-3968"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nigel Cannings","raw_affiliation_strings":["Intelligent Voice Ltd,London,UK","Intelligent Voice Ltd, London, UK"],"affiliations":[{"raw_affiliation_string":"Intelligent Voice Ltd,London,UK","institution_ids":["https://openalex.org/I4210153682"]},{"raw_affiliation_string":"Intelligent Voice Ltd, London, UK","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051257462","display_name":"Vito Veneziano","orcid":null},"institutions":[{"id":"https://openalex.org/I141584323","display_name":"University of Hertfordshire","ror":"https://ror.org/0267vjk41","country_code":"GB","type":"education","lineage":["https://openalex.org/I141584323"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vito Veneziano","raw_affiliation_strings":["School of Physics,Engineering and Computer Science, University of Hertfordshire,Hatfield,UK","School of Physics,Engineering and Computer Science, University of Hertfordshire, Hatfield, UK"],"affiliations":[{"raw_affiliation_string":"School of Physics,Engineering and Computer Science, University of Hertfordshire,Hatfield,UK","institution_ids":["https://openalex.org/I141584323"]},{"raw_affiliation_string":"School of Physics,Engineering and Computer Science, University of Hertfordshire, Hatfield, UK","institution_ids":["https://openalex.org/I141584323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078794661","display_name":"Yi Sun","orcid":"https://orcid.org/0000-0002-9817-8004"},"institutions":[{"id":"https://openalex.org/I141584323","display_name":"University of Hertfordshire","ror":"https://ror.org/0267vjk41","country_code":"GB","type":"education","lineage":["https://openalex.org/I141584323"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yi Sun","raw_affiliation_strings":["School of Physics,Engineering and Computer Science, University of Hertfordshire,Hatfield,UK","School of Physics,Engineering and Computer Science, University of Hertfordshire, Hatfield, UK"],"affiliations":[{"raw_affiliation_string":"School of Physics,Engineering and Computer Science, University of Hertfordshire,Hatfield,UK","institution_ids":["https://openalex.org/I141584323"]},{"raw_affiliation_string":"School of Physics,Engineering and Computer Science, University of Hertfordshire, Hatfield, UK","institution_ids":["https://openalex.org/I141584323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069587466"],"corresponding_institution_ids":["https://openalex.org/I141584323","https://openalex.org/I4210153682"],"apc_list":null,"apc_paid":null,"fwci":0.6913,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70490196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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":1.0,"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":1.0,"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":0.9986000061035156,"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":0.9976000189781189,"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":0.7657307386398315},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7434898614883423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.588270902633667},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5386995673179626},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5340104699134827},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.45925280451774597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.421661376953125},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.41088926792144775},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37446272373199463},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09609648585319519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657307386398315},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7434898614883423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.588270902633667},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5386995673179626},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5340104699134827},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.45925280451774597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.421661376953125},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.41088926792144775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37446272373199463},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09609648585319519},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9891882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9891882","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:uhra.herts.ac.uk:2299/27076","is_oa":false,"landing_page_url":"http://hdl.handle.net/2299/27076","pdf_url":null,"source":{"id":"https://openalex.org/S4306400241","display_name":"University of Hertfordshire Research Archive (University of Hertfordshire)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I141584323","host_organization_name":"University of Hertfordshire","host_organization_lineage":["https://openalex.org/I141584323"],"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":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G4046169599","display_name":null,"funder_award_id":"823907","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W242445121","https://openalex.org/W1508165687","https://openalex.org/W1543974205","https://openalex.org/W1964469912","https://openalex.org/W2030931454","https://openalex.org/W2090040091","https://openalex.org/W2109896588","https://openalex.org/W2127141656","https://openalex.org/W2146334809","https://openalex.org/W2191779130","https://openalex.org/W2295001676","https://openalex.org/W2471136870","https://openalex.org/W2618530766","https://openalex.org/W2785373015","https://openalex.org/W2803193013","https://openalex.org/W2886300652","https://openalex.org/W2890104572","https://openalex.org/W2944458161","https://openalex.org/W2964300796","https://openalex.org/W2973049979","https://openalex.org/W3000724186","https://openalex.org/W3008392994","https://openalex.org/W3013295773","https://openalex.org/W3019220897","https://openalex.org/W3036601975","https://openalex.org/W3104377639","https://openalex.org/W3126625480","https://openalex.org/W3154585115","https://openalex.org/W3161428216","https://openalex.org/W3162589478","https://openalex.org/W3173751215","https://openalex.org/W3175709363","https://openalex.org/W3196711847","https://openalex.org/W3197642003","https://openalex.org/W3198429080","https://openalex.org/W3207346153","https://openalex.org/W3213879871","https://openalex.org/W4206675400","https://openalex.org/W4235140846","https://openalex.org/W4287637191","https://openalex.org/W4297997662","https://openalex.org/W4385245566","https://openalex.org/W6673163045","https://openalex.org/W6687152286","https://openalex.org/W6739901393","https://openalex.org/W6747534529","https://openalex.org/W6779919476","https://openalex.org/W6794988970"],"related_works":["https://openalex.org/W3176621072","https://openalex.org/W4293226380","https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W4321487865","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2995475466","https://openalex.org/W4313906399","https://openalex.org/W2090259340"],"abstract_inverted_index":{"Creating":[0],"speech":[1,22,70],"emotion":[2,51,71,139],"recognition":[3,52],"models":[4,92,127],"com-parable":[5],"to":[6,56,134],"the":[7,19,35,57,76,79,90,100,130,135],"capability":[8],"of":[9,21,78,113,137],"how":[10],"humans":[11],"recognise":[12],"emotions":[13],"is":[14,64],"a":[15],"long-standing":[16],"challenge":[17],"in":[18,99,117,125],"field":[20],"technology":[23],"with":[24,132],"many":[25,38],"potential":[26],"commercial":[27],"applications.":[28],"As":[29],"transformer-based":[30,91,126],"architectures":[31,119],"have":[32],"recently":[33],"become":[34],"state-of-the-art":[36],"for":[37,49,83],"natural":[39],"language":[40],"processing":[41],"related":[42],"applications,":[43],"this":[44],"paper":[45,105],"investigates":[46],"their":[47,94],"suitability":[48],"acoustic":[50],"and":[53,120],"compares":[54],"them":[55],"well-known":[58],"AlexNet":[59],"convolutional":[60,95],"approach.":[61],"This":[62,104],"comparison":[63],"made":[65],"using":[66],"several":[67],"publicly":[68],"available":[69],"corpora.":[72],"Experimental":[73],"results":[74,87],"demonstrate":[75],"efficacy":[77],"different":[80,138],"architectural":[81],"approaches":[82],"particular":[84],"emotions.":[85],"The":[86],"show":[88],"that":[89],"outperform":[93],"counterparts":[96],"yielding":[97],"F1-scores":[98],"range":[101],"[70.33%,":[102],"75.76%].":[103],"further":[106],"provides":[107],"insights":[108],"via":[109],"dimensionality":[110],"reduction":[111],"analysis":[112],"output":[114],"layer":[115],"activations":[116],"both":[118],"reveals":[121],"significantly":[122],"improved":[123],"clustering":[124],"whilst":[128],"highlighting":[129],"nuances":[131],"regard":[133],"separability":[136],"classes.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}