{"id":"https://openalex.org/W4367172564","doi":"https://doi.org/10.1080/09540091.2023.2189217","title":"Multi-branch feature learning based speech emotion recognition using SCAR-NET","display_name":"Multi-branch feature learning based speech emotion recognition using SCAR-NET","publication_year":2023,"publication_date":"2023-04-27","ids":{"openalex":"https://openalex.org/W4367172564","doi":"https://doi.org/10.1080/09540091.2023.2189217"},"language":"en","primary_location":{"id":"doi:10.1080/09540091.2023.2189217","is_oa":true,"landing_page_url":"https://doi.org/10.1080/09540091.2023.2189217","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/09540091.2023.2189217?needAccess=true&role=button","source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":true,"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","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.tandfonline.com/doi/pdf/10.1080/09540091.2023.2189217?needAccess=true&role=button","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062098757","display_name":"Keji Mao","orcid":"https://orcid.org/0000-0002-5021-378X"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keji Mao","raw_affiliation_strings":["College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394394","display_name":"Yuxiang Wang","orcid":"https://orcid.org/0000-0002-6945-6431"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Wang","raw_affiliation_strings":["College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101131597","display_name":"Ligang Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ligang Ren","raw_affiliation_strings":["College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120798275","display_name":"Jinhong Zhang","orcid":"https://orcid.org/0000-0002-9906-3508"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhong Zhang","raw_affiliation_strings":["College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024406603","display_name":"Jiefan Qiu","orcid":"https://orcid.org/0000-0003-2198-1875"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiefan Qiu","raw_affiliation_strings":["College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064544383","display_name":"Guanglin Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guanglin Dai","raw_affiliation_strings":["College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology College of Software, Zhejiang University of Technology, Hangzhou, People's Republic of China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5064544383"],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":{"value":1270,"currency":"USD","value_usd":1270},"apc_paid":{"value":1270,"currency":"USD","value_usd":1270},"fwci":3.3704,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92660301,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"35","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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/T10057","display_name":"Face and Expression Recognition","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9951000213623047,"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":0.7518275380134583},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6377215385437012},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6277036666870117},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.521872878074646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.503018319606781},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4812876582145691},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4736674427986145},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.4287920594215393},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3275718688964844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7518275380134583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6377215385437012},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6277036666870117},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.521872878074646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503018319606781},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4812876582145691},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4736674427986145},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.4287920594215393},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3275718688964844},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/09540091.2023.2189217","is_oa":true,"landing_page_url":"https://doi.org/10.1080/09540091.2023.2189217","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/09540091.2023.2189217?needAccess=true&role=button","source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":true,"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","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:98092f9487a74ff8a2072b5677cf3603","is_oa":true,"landing_page_url":"https://doaj.org/article/98092f9487a74ff8a2072b5677cf3603","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":"Connection Science, Vol 35, Iss 1 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1080/09540091.2023.2189217","is_oa":true,"landing_page_url":"https://doi.org/10.1080/09540091.2023.2189217","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/09540091.2023.2189217?needAccess=true&role=button","source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":true,"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","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G589977349","display_name":null,"funder_award_id":"62072410","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4367172564.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1803168886","https://openalex.org/W1844030040","https://openalex.org/W1974784407","https://openalex.org/W2081420711","https://openalex.org/W2111926505","https://openalex.org/W2132664937","https://openalex.org/W2156503193","https://openalex.org/W2158061940","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2313507061","https://openalex.org/W2399733683","https://openalex.org/W2487114723","https://openalex.org/W2547616654","https://openalex.org/W2576674859","https://openalex.org/W2587299955","https://openalex.org/W2625297138","https://openalex.org/W2803193013","https://openalex.org/W2884739346","https://openalex.org/W2889191349","https://openalex.org/W2889544113","https://openalex.org/W2909327627","https://openalex.org/W2962949934","https://openalex.org/W2963559999","https://openalex.org/W2963631961","https://openalex.org/W2997700007","https://openalex.org/W3015449518","https://openalex.org/W3034190797","https://openalex.org/W3084484668","https://openalex.org/W3095648847","https://openalex.org/W3109961563","https://openalex.org/W3134450397","https://openalex.org/W3204087964","https://openalex.org/W4200333562","https://openalex.org/W4205496101","https://openalex.org/W4205633160","https://openalex.org/W4210723357","https://openalex.org/W4214883719","https://openalex.org/W4221059245","https://openalex.org/W4221136155","https://openalex.org/W4224001749","https://openalex.org/W4241231692","https://openalex.org/W4250685322","https://openalex.org/W4293691212","https://openalex.org/W4307548253","https://openalex.org/W4316659981"],"related_works":["https://openalex.org/W2912321008","https://openalex.org/W1998607122","https://openalex.org/W2324368075","https://openalex.org/W2905271011","https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W3164948662","https://openalex.org/W4289536128","https://openalex.org/W3153597579","https://openalex.org/W4298151006"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,143],"recognition":[2],"(SER)":[3],"is":[4],"an":[5,50],"active":[6],"research":[7],"area":[8,28],"in":[9,26],"affective":[10],"computing.":[11],"Recognizing":[12],"emotions":[13],"from":[14,59],"speech":[15,60,142],"signals":[16,61],"helps":[17],"to":[18,55,111,124],"assess":[19],"human":[20],"behaviour,":[21],"which":[22,132],"has":[23],"promising":[24],"applications":[25],"the":[27,126,141,152],"of":[29,34,122,130,154],"human-computer":[30],"interaction.":[31],"The":[32,96],"performance":[33],"deep":[35,93],"learning-based":[36],"SER":[37],"methods":[38],"relies":[39],"heavily":[40],"on":[41,140],"feature":[42,94],"learning.":[43,95],"In":[44],"this":[45],"paper,":[46],"we":[47,72],"propose":[48],"SCAR-NET,":[49],"improved":[51],"convolutional":[52],"neural":[53],"network,":[54],"extract":[56,73],"emotional":[57],"features":[58,79,97],"and":[62,76,84,105,128,137,147],"implement":[63],"classification.":[64],"This":[65],"work":[66],"includes":[67],"two":[68],"main":[69],"parts:":[70],"First,":[71],"spectral,":[74],"temporal,":[75],"spectral-temporal":[77],"correlation":[78],"through":[80,107],"three":[81],"parallel":[82],"paths;":[83],"then":[85],"split-convolve-aggregate":[86],"residual":[87],"blocks":[88],"are":[89,98],"designed":[90],"for":[91,114],"multi-branch":[92],"refined":[99],"by":[100],"global":[101],"average":[102],"pooling":[103],"(GAP)":[104],"pass":[106],"a":[108,120],"softmax":[109],"classifier":[110],"generate":[112],"predictions":[113],"different":[115],"emotions.":[116],"We":[117],"also":[118],"conduct":[119],"series":[121],"experiments":[123],"evaluate":[125],"robustness":[127],"effectiveness":[129],"SCAR-NET":[131],"can":[133],"achieve":[134],"96.45%,":[135],"83.13%,":[136],"89.93%":[138],"accuracy":[139],"datasets":[144],"EMO-DB,":[145],"SAVEE,":[146],"RAVDESS.":[148],"These":[149],"results":[150],"show":[151],"outperformance":[153],"SCAR-NET.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}