{"id":"https://openalex.org/W4393118224","doi":"https://doi.org/10.1109/access.2024.3439604","title":"emoDARTS: Joint Optimization of CNN and Sequential Neural Network Architectures for Superior Speech Emotion Recognition","display_name":"emoDARTS: Joint Optimization of CNN and Sequential Neural Network Architectures for Superior Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4393118224","doi":"https://doi.org/10.1109/access.2024.3439604"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3439604","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3439604","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3439604","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070541195","display_name":"Thejan Rajapakshe","orcid":"https://orcid.org/0000-0003-3156-3327"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thejan Rajapakshe","raw_affiliation_strings":["School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3156-3327","affiliations":[{"raw_affiliation_string":"School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, Australia","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080929578","display_name":"Rajib Rana","orcid":"https://orcid.org/0000-0002-0506-2409"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rajib Rana","raw_affiliation_strings":["School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, Australia","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064983246","display_name":"Sara Khalifa","orcid":"https://orcid.org/0000-0002-3417-2834"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sara Khalifa","raw_affiliation_strings":["School of Information Systems, Queensland University of Technology, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3417-2834","affiliations":[{"raw_affiliation_string":"School of Information Systems, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001303929","display_name":"Berrak \u015ei\u015fman","orcid":"https://orcid.org/0000-0001-8078-3305"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":["The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-8078-3305","affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6478-8699","affiliations":[{"raw_affiliation_string":"Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-4075-4072","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":3.0316,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92138977,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"110492","last_page":"110503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9790999889373779,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9790999889373779,"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":0.9717000126838684,"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/joint","display_name":"Joint (building)","score":0.7583199739456177},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7114675045013428},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.626367449760437},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5378685593605042},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4668259024620056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3838185667991638},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12215566635131836}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7583199739456177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7114675045013428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.626367449760437},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5378685593605042},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4668259024620056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3838185667991638},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12215566635131836},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/access.2024.3439604","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3439604","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2403.14083","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.14083","pdf_url":"https://arxiv.org/pdf/2403.14083","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:115265","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-1152658","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/115265/emoDARTS_Joint_Optimization_of_CNN_and_Sequential_Neural_Network_Architectures_for_Superior_Speech_Emotion_Recognition.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:bcda6580f6564b93aa600038eb150ac4","is_oa":true,"landing_page_url":"https://doaj.org/article/bcda6580f6564b93aa600038eb150ac4","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 12, Pp 110492-110503 (2024)","raw_type":"article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1772973","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1772973","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3439604","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3439604","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2148154194","https://openalex.org/W2181741066","https://openalex.org/W2191779130","https://openalex.org/W2342475039","https://openalex.org/W2399733683","https://openalex.org/W2742542661","https://openalex.org/W2806051338","https://openalex.org/W2885005742","https://openalex.org/W2888964888","https://openalex.org/W2889286050","https://openalex.org/W2889717020","https://openalex.org/W2963821229","https://openalex.org/W2972602947","https://openalex.org/W2973037561","https://openalex.org/W2995517008","https://openalex.org/W2997958863","https://openalex.org/W3034609471","https://openalex.org/W3096136448","https://openalex.org/W3132349482","https://openalex.org/W3160945783","https://openalex.org/W3161428216","https://openalex.org/W4213439605","https://openalex.org/W4221162872","https://openalex.org/W4225320271","https://openalex.org/W4225694800","https://openalex.org/W4312209192","https://openalex.org/W4312327819","https://openalex.org/W4385822707","https://openalex.org/W6729956949","https://openalex.org/W6747668270","https://openalex.org/W6752515464","https://openalex.org/W6767994309","https://openalex.org/W6771784742","https://openalex.org/W6773935006","https://openalex.org/W6853054785"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2888483922","https://openalex.org/W2367747139","https://openalex.org/W4391102217","https://openalex.org/W2566187525","https://openalex.org/W2566334511","https://openalex.org/W2391251536","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"is":[4,65],"crucial":[5],"for":[6,53,70,126],"enabling":[7],"computers":[8],"to":[9,104,113],"understand":[10],"the":[11,24,56,97,145,149,156,161,175,189],"emotions":[12],"conveyed":[13],"in":[14,20,132],"human":[15],"communication.":[16],"With":[17],"recent":[18],"advancements":[19],"Deep":[21],"Learning":[22],"(DL),":[23],"performance":[25],"of":[26,99,148],"SER":[27,92,177],"models":[28,172],"has":[29,109],"significantly":[30],"improved.":[31],"However,":[32],"designing":[33],"an":[34],"optimal":[35,72],"DL":[36,58],"architecture":[37,89],"requires":[38],"specialised":[39],"knowledge":[40],"and":[41,82,101,116,129,173,192],"experimental":[42],"assessments.":[43],"Fortunately,":[44],"Neural":[45,84],"Architecture":[46,62],"Search":[47,63],"(NAS)":[48],"provides":[49],"a":[50,66,78,123],"potential":[51],"solution":[52],"automatically":[54],"determining":[55],"best":[57,157],"model.":[59],"The":[60,94],"Differentiable":[61],"(DARTS)":[64],"particularly":[67],"efficient":[68],"method":[69],"discovering":[71],"models.":[73],"This":[74],"study":[75],"presents":[76],"emoDARTS,":[77],"DARTS-optimised":[79],"joint":[80],"CNN":[81,100,115,128],"Sequential":[83],"Network":[85],"(SeqNN:":[86],"LSTM,":[87],"RNN)":[88],"that":[90,166],"enhances":[91],"performance.":[93,106],"literature":[95],"supports":[96],"selection":[98],"LSTM":[102,117],"coupling":[103],"improve":[105],"While":[107],"DARTS":[108,154,162,181],"previously":[110],"been":[111],"used":[112],"choose":[114,155],"operations":[118,131],"independently,":[119],"our":[120,186],"technique":[121],"adds":[122],"novel":[124],"mechanism":[125],"selecting":[127],"SeqNN":[130],"conjunction":[133],"using":[134],"DARTS.":[135],"Unlike":[136],"earlier":[137],"work,":[138],"we":[139,152],"do":[140],"not":[141],"impose":[142],"limits":[143],"on":[144,182,188],"layer":[146,158],"order":[147,159],"CNN.":[150],"Instead,":[151],"let":[153],"inside":[160],"cell.":[163],"We":[164],"demonstrate":[165],"emoDARTS":[167],"outperforms":[168],"conventionally":[169],"designed":[170],"CNN-LSTM":[171,183],"surpasses":[174],"best-reported":[176],"results":[178],"achieved":[179],"through":[180],"by":[184],"evaluating":[185],"approach":[187],"IEMOCAP,":[190],"MSP-IMPROV,":[191],"MSP-Podcast":[193],"datasets.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2024-03-24T00:00:00"}