{"id":"https://openalex.org/W4376874355","doi":"https://doi.org/10.1080/21681163.2023.2212082","title":"Multi-modal speech emotion detection using optimised deep neural network classifier","display_name":"Multi-modal speech emotion detection using optimised deep neural network classifier","publication_year":2023,"publication_date":"2023-05-17","ids":{"openalex":"https://openalex.org/W4376874355","doi":"https://doi.org/10.1080/21681163.2023.2212082"},"language":"en","primary_location":{"id":"doi:10.1080/21681163.2023.2212082","is_oa":false,"landing_page_url":"https://doi.org/10.1080/21681163.2023.2212082","pdf_url":null,"source":{"id":"https://openalex.org/S2764763012","display_name":"Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization","issn_l":"2168-1163","issn":["2168-1163","2168-1171"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"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/A5091964954","display_name":"Sweta Nishant Padman","orcid":"https://orcid.org/0000-0002-1386-9544"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sweta Nishant Padman","raw_affiliation_strings":["Department of Electronics and Telecommunication, Ramrao Adik Institute of Technology, Navi Mumbai, Maharashtra, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Telecommunication, Ramrao Adik Institute of Technology, Navi Mumbai, Maharashtra, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087566967","display_name":"Dhiraj Magare","orcid":"https://orcid.org/0000-0002-1904-5271"},"institutions":[{"id":"https://openalex.org/I4210145126","display_name":"Aditya Birla (India)","ror":"https://ror.org/03pztks36","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210145126"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dhiraj Magare","raw_affiliation_strings":["Department of Electronics Engineering, Ramrao Adik Institute of Technology CollegeSector 7, Navi Mumbai, Maharashtra, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Ramrao Adik Institute of Technology CollegeSector 7, Navi Mumbai, Maharashtra, India","institution_ids":["https://openalex.org/I4210145126"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091964954"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7848,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72316722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"11","issue":"5","first_page":"2020","last_page":"2038"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9904000163078308,"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":0.7502272725105286},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6887099742889404},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6863721013069153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6690088510513306},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6244730949401855},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5580052733421326},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5554788112640381},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5143169164657593},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48683470487594604},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4441748261451721},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4285355806350708},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42679983377456665},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32742273807525635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7502272725105286},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6887099742889404},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6863721013069153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6690088510513306},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6244730949401855},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5580052733421326},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5554788112640381},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5143169164657593},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48683470487594604},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4441748261451721},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4285355806350708},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42679983377456665},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32742273807525635},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/21681163.2023.2212082","is_oa":false,"landing_page_url":"https://doi.org/10.1080/21681163.2023.2212082","pdf_url":null,"source":{"id":"https://openalex.org/S2764763012","display_name":"Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization","issn_l":"2168-1163","issn":["2168-1163","2168-1171"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W115681963","https://openalex.org/W159326959","https://openalex.org/W2074788634","https://openalex.org/W2081835714","https://openalex.org/W2177486042","https://openalex.org/W2306115793","https://openalex.org/W2397175282","https://openalex.org/W2591380794","https://openalex.org/W2799331981","https://openalex.org/W2924116307","https://openalex.org/W2940359106","https://openalex.org/W2964370293","https://openalex.org/W2966935339","https://openalex.org/W2971275122","https://openalex.org/W3000373873","https://openalex.org/W3008039831","https://openalex.org/W3012888109","https://openalex.org/W3016092640","https://openalex.org/W3037243813","https://openalex.org/W3040522169","https://openalex.org/W3098571047","https://openalex.org/W3104763483","https://openalex.org/W3112103486","https://openalex.org/W3120709499","https://openalex.org/W3127521573","https://openalex.org/W3144907487","https://openalex.org/W3158929093","https://openalex.org/W3177927575","https://openalex.org/W3184672723","https://openalex.org/W3200866700","https://openalex.org/W4214825215","https://openalex.org/W4221121088","https://openalex.org/W4255159906","https://openalex.org/W4288081307"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4318719684","https://openalex.org/W4389724018","https://openalex.org/W4387914125","https://openalex.org/W3105646692","https://openalex.org/W2584926856","https://openalex.org/W3212086526","https://openalex.org/W2014713986"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,73,98],"recognition":[2],"(SER)":[3],"has":[4],"received":[5],"significant":[6],"attention":[7],"recently":[8],"and":[9,173,182,190,193],"seems":[10],"to":[11,87,121,143],"be":[12],"a":[13,49],"critical":[14],"aspect":[15],"of":[16,21,69,158],"human-computer":[17],"interaction.":[18],"The":[19,59,114,132,155],"performance":[20,96],"the":[22,28,42,66,70,81,100,105,109,139,145,159,169,174,186],"recent":[23],"methods":[24],"is":[25,62,76,85,119,136],"not":[26],"at":[27],"expected":[29],"level":[30],"there":[31],"are":[32],"many":[33],"different":[34],"strategies":[35],"have":[36,165],"been":[37,166],"developed":[38],"for":[39,64,185,195],"SER.":[40],"In":[41,78],"present":[43],"situation,":[44],"communication,":[45],"non-verbal":[46],"vocalisation,":[47],"with":[48,152],"vocal":[50],"sound":[51],"plays":[52],"an":[53],"essential":[54],"role":[55],"in":[56,97,108,138,149],"emotional":[57],"expression.":[58],"multimodal":[60,91],"database":[61,172],"considered":[63],"which":[65],"hybridised":[67],"model":[68,75],"audio-visual":[71],"dependent":[72],"identification":[74],"proposed.":[77],"this":[79],"research,":[80],"optimised":[82],"deep":[83,110,140,163],"NN":[84,111,141,164],"used":[86,137],"recognise":[88],"emotions":[89],"from":[90,125],"input":[92],"data.":[93,198],"For":[94],"better":[95],"recognition,":[99],"learner":[101,133,160],"memorising":[102,134,161],"optimisation":[103,135],"fine-tunes":[104],"hyperparameters":[106],"involved":[107,148],"network":[112],"classifier.":[113],"hybrid":[115],"texture":[116],"feature":[117],"descriptor":[118],"proposed":[120,175],"improve":[122],"classification":[123],"outcomes":[124],"audio-video":[126],"signals":[127],"as":[128,130],"well":[129],"accuracy.":[131,154],"classifier":[142],"obtain":[144],"ideal":[146],"parameters":[147],"exploring":[150],"space":[151],"high":[153],"metric":[156],"values":[157],"optimisation-based":[162],"evaluated":[167],"using":[168],"Enter":[170],"face\u201905":[171],"method":[176],"obtained":[177],"97.490%":[178,183],"accuracy,":[179],"98%":[180],"sensitivity,":[181],"specificity":[184],"K-fold":[187],"value":[188],"10%":[189],"96.928%,":[191],"98.80%,":[192],"96.928%":[194],"90%":[196],"training":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}