{"id":"https://openalex.org/W4387789875","doi":"https://doi.org/10.1109/access.2023.3326071","title":"Speech Emotion Recognition and Deep Learning: An Extensive Validation Using Convolutional Neural Networks","display_name":"Speech Emotion Recognition and Deep Learning: An Extensive Validation Using Convolutional Neural Networks","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387789875","doi":"https://doi.org/10.1109/access.2023.3326071"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3326071","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3326071","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10287976.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10287976.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032756614","display_name":"Francesco Ardan Dal R\u00ec","orcid":"https://orcid.org/0009-0001-1806-2459"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]},{"id":"https://openalex.org/I4210118054","display_name":"Conservatorio di Musica FA Bonporti Trento","ror":"https://ror.org/02bxn5a88","country_code":"IT","type":"education","lineage":["https://openalex.org/I4210118054"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Ardan Dal R\u00ed","raw_affiliation_strings":["Department of Information Engineering and Computer Science (DISI), University of Trento, Povo, Trento, Italy","Department of Electronic Music, Via S. Giovanni Bosco 4, Conservatory of Music F. A. Bonporti, Trento, IT","DISI - Department of Information Engineering and Computer Science, via Sommarive 9, University of Trento, Povo (TN), IT"],"raw_orcid":"https://orcid.org/0009-0001-1806-2459","affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science (DISI), University of Trento, Povo, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]},{"raw_affiliation_string":"Department of Electronic Music, Via S. Giovanni Bosco 4, Conservatory of Music F. A. Bonporti, Trento, IT","institution_ids":["https://openalex.org/I4210118054"]},{"raw_affiliation_string":"DISI - Department of Information Engineering and Computer Science, via Sommarive 9, University of Trento, Povo (TN), IT","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071555746","display_name":"Fabio Cifariello Ciardi","orcid":"https://orcid.org/0000-0003-3802-780X"},"institutions":[{"id":"https://openalex.org/I4210118054","display_name":"Conservatorio di Musica FA Bonporti Trento","ror":"https://ror.org/02bxn5a88","country_code":"IT","type":"education","lineage":["https://openalex.org/I4210118054"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Cifariello Ciardi","raw_affiliation_strings":["Department of Electronic Music, Conservatory of Music F. A. Bonporti, Trento, Italy","Department of Electronic Music, Via S. Giovanni Bosco 4, Conservatory of Music F. A. Bonporti, Trento, IT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Music, Conservatory of Music F. A. Bonporti, Trento, Italy","institution_ids":["https://openalex.org/I4210118054"]},{"raw_affiliation_string":"Department of Electronic Music, Via S. Giovanni Bosco 4, Conservatory of Music F. A. Bonporti, Trento, IT","institution_ids":["https://openalex.org/I4210118054"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073436476","display_name":"Nicola Conci","orcid":"https://orcid.org/0000-0002-7858-0928"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Conci","raw_affiliation_strings":["Department of Information Engineering and Computer Science (DISI), University of Trento, Povo, Trento, Italy","DISI - Department of Information Engineering and Computer Science, via Sommarive 9, University of Trento, Povo (TN), IT"],"raw_orcid":"https://orcid.org/0000-0002-7858-0928","affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science (DISI), University of Trento, Povo, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]},{"raw_affiliation_string":"DISI - Department of Information Engineering and Computer Science, via Sommarive 9, University of Trento, Povo (TN), IT","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":8.1826,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.98314817,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"11","issue":null,"first_page":"116638","last_page":"116649"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.998199999332428,"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":0.998199999332428,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9896000027656555,"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":0.8308497071266174},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6673693656921387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5703953504562378},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5518937706947327},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5467891693115234},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5435618162155151},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.5289444923400879},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5072205066680908},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49054330587387085},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43005454540252686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36077138781547546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308497071266174},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6673693656921387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5703953504562378},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5518937706947327},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5467891693115234},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5435618162155151},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.5289444923400879},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5072205066680908},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49054330587387085},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43005454540252686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36077138781547546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2023.3326071","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3326071","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10287976.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:iris.unitn.it:11572/406850","is_oa":true,"landing_page_url":"https://hdl.handle.net/11572/406850","pdf_url":"https://iris.unitn.it/bitstream/11572/406850/1/Speech_Emotion_Recognition_and_Deep_Learning_An_Extensive_Validation_Using_Convolutional_Neural_Networks.pdf","source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:9f028b1343444ae7b36e62eaa628f4e1","is_oa":true,"landing_page_url":"https://doaj.org/article/9f028b1343444ae7b36e62eaa628f4e1","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 116638-116649 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3326071","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3326071","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10287976.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387789875.pdf","grobid_xml":"https://content.openalex.org/works/W4387789875.grobid-xml"},"referenced_works_count":81,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1522301498","https://openalex.org/W1972280480","https://openalex.org/W1981077332","https://openalex.org/W2003653478","https://openalex.org/W2030931454","https://openalex.org/W2074788634","https://openalex.org/W2090777335","https://openalex.org/W2090832870","https://openalex.org/W2111926505","https://openalex.org/W2122348661","https://openalex.org/W2146334809","https://openalex.org/W2154024118","https://openalex.org/W2171321155","https://openalex.org/W2187089797","https://openalex.org/W2295001676","https://openalex.org/W2342475039","https://openalex.org/W2399733683","https://openalex.org/W2590096887","https://openalex.org/W2598207902","https://openalex.org/W2792311129","https://openalex.org/W2800126857","https://openalex.org/W2803193013","https://openalex.org/W2806046733","https://openalex.org/W2884585870","https://openalex.org/W2899663614","https://openalex.org/W2905903577","https://openalex.org/W2936113082","https://openalex.org/W2950518992","https://openalex.org/W2951589696","https://openalex.org/W2962686539","https://openalex.org/W2964370293","https://openalex.org/W2969889150","https://openalex.org/W2972724712","https://openalex.org/W2976594877","https://openalex.org/W2997399314","https://openalex.org/W3008039831","https://openalex.org/W3015884429","https://openalex.org/W3042183479","https://openalex.org/W3047207526","https://openalex.org/W3093863290","https://openalex.org/W3094273504","https://openalex.org/W3096262466","https://openalex.org/W3096284638","https://openalex.org/W3097341095","https://openalex.org/W3097969370","https://openalex.org/W3103455915","https://openalex.org/W3109943296","https://openalex.org/W3112103486","https://openalex.org/W3114195756","https://openalex.org/W3136524425","https://openalex.org/W3139270985","https://openalex.org/W3158346300","https://openalex.org/W3161659450","https://openalex.org/W3163179600","https://openalex.org/W3177602233","https://openalex.org/W3197558301","https://openalex.org/W3209219832","https://openalex.org/W3216148133","https://openalex.org/W4200174246","https://openalex.org/W4205131079","https://openalex.org/W4221072225","https://openalex.org/W4232282348","https://openalex.org/W4285144065","https://openalex.org/W4285410993","https://openalex.org/W4285815884","https://openalex.org/W4296523924","https://openalex.org/W4296994433","https://openalex.org/W4297841699","https://openalex.org/W4309708680","https://openalex.org/W4310154196","https://openalex.org/W4313315386","https://openalex.org/W4318570632","https://openalex.org/W4318831690","https://openalex.org/W4375868941","https://openalex.org/W6631190155","https://openalex.org/W6693178250","https://openalex.org/W6743587472","https://openalex.org/W6755977528","https://openalex.org/W6764686110","https://openalex.org/W6805654738"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4375867731","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"The":[0],"domain":[1],"of":[2,16,34,42,60,67,75,113,118,144,166,176],"Speech":[3],"Emotion":[4],"Recognition":[5],"(SER)":[6],"has":[7,20],"experienced":[8],"a":[9,29,40,57,65,100,105,111,116,141],"tremendous":[10],"revolution":[11],"due":[12,71],"to":[13,28,39,72,161,171],"the":[14,73,85,134,169,173,177],"outbreak":[15],"deep":[17],"learning,":[18],"which":[19,46],"contributed,":[21],"as":[22],"in":[23,32,92],"many":[24],"other":[25],"research":[26],"areas,":[27],"significant":[30],"boost":[31],"terms":[33],"model":[35,102],"accuracy.":[36],"SER":[37,62,125],"refers":[38],"branch":[41],"Human-Computer":[43],"Interaction":[44],"(HCI),":[45],"deals":[47],"with":[48,104,168],"recognizing":[49],"emotional":[50,158],"states":[51],"from":[52],"human":[53],"speech.":[54],"Although":[55],"being":[56],"thriving":[58],"field":[59],"research,":[61],"still":[63],"poses":[64],"number":[66],"non-trivial":[68],"challenges,":[69],"mainly":[70],"lack":[74],"shared":[76],"best":[77],"practices":[78],"and":[79,109,130,148],"high-quality":[80],"datasets":[81,121,163],"that":[82],"can":[83],"make":[84],"developed":[86],"models":[87],"suitable":[88],"for":[89,124],"their":[90],"application":[91],"real":[93],"environments.":[94],"In":[95],"this":[96],"paper,":[97],"we":[98,151],"implement":[99],"CNN-based":[101],"combined":[103],"Convolutional":[106],"Attention":[107],"Block,":[108],"conduct":[110],"series":[112],"experiments":[114],"involving":[115],"selection":[117],"four":[119],"English":[120],"popularly":[122],"used":[123],"applications:":[126],"RAVDESS,":[127],"TESS,":[128],"CREMA-D,":[129],"IEMOCAP.":[131],"After":[132],"testing":[133],"proposed":[135],"pipeline":[136],"on":[137],"individual":[138],"datasets,":[139],"achieving":[140],"mean":[142],"accuracy":[143],"83%,":[145],"100%,":[146],"68%":[147],"63%":[149],"respectively,":[150],"perform":[152],"an":[153],"extensive":[154],"cross-validation":[155],"between":[156],"common":[157],"classes":[159],"belonging":[160],"single":[162],"or":[164],"combinations":[165],"them,":[167],"aim":[170],"investigate":[172],"generalization":[174],"abilities":[175],"extracted":[178],"features.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2023-10-20T00:00:00"}