{"id":"https://openalex.org/W4400905332","doi":"https://doi.org/10.1109/access.2024.3432813","title":"A Lightweight Multi-Scale Model for Speech Emotion Recognition","display_name":"A Lightweight Multi-Scale Model for Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400905332","doi":"https://doi.org/10.1109/access.2024.3432813"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3432813","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3432813","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":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://doi.org/10.1109/access.2024.3432813","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003898243","display_name":"Hengduo Li","orcid":"https://orcid.org/0009-0000-0433-2609"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoming Li","raw_affiliation_strings":["School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0009-0000-0433-2609","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083796111","display_name":"Daqi Zhao","orcid":"https://orcid.org/0009-0007-7287-8786"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daqi Zhao","raw_affiliation_strings":["School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0009-0007-7287-8786","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113240734","display_name":"Jingwen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwen Wang","raw_affiliation_strings":["School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101578019","display_name":"Deqiang Wang","orcid":"https://orcid.org/0000-0003-0003-4406"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deqiang Wang","raw_affiliation_strings":["School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-0003-4406","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003898243"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.8713,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85625641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"130228","last_page":"130240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9901000261306763,"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":0.9901000261306763,"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":0.9526000022888184,"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":0.8640367984771729},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.7851284742355347},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7075029611587524},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6265785694122314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5628207325935364},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5337138175964355},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5311728119850159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4802860915660858},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47532251477241516},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4381585121154785},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42463260889053345},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41600915789604187},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4093533754348755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8640367984771729},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7851284742355347},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7075029611587524},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6265785694122314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5628207325935364},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5337138175964355},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5311728119850159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4802860915660858},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47532251477241516},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4381585121154785},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42463260889053345},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41600915789604187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4093533754348755},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3432813","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3432813","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9289717476b8454b96b731c7ca745e8a","is_oa":true,"landing_page_url":"https://doaj.org/article/9289717476b8454b96b731c7ca745e8a","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 130228-130240 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3432813","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3432813","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":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":[{"id":"https://openalex.org/G7394729620","display_name":null,"funder_award_id":"2020YFC0833203","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1559788381","https://openalex.org/W2097117768","https://openalex.org/W2146334809","https://openalex.org/W2161073241","https://openalex.org/W2187089797","https://openalex.org/W2295001676","https://openalex.org/W2520774990","https://openalex.org/W2558398546","https://openalex.org/W2625297138","https://openalex.org/W2766272105","https://openalex.org/W2885005742","https://openalex.org/W2889374687","https://openalex.org/W2889717020","https://openalex.org/W2940259008","https://openalex.org/W2997399314","https://openalex.org/W3015969913","https://openalex.org/W3037545100","https://openalex.org/W3092248280","https://openalex.org/W3094897602","https://openalex.org/W3097149715","https://openalex.org/W3139270985","https://openalex.org/W3145643603","https://openalex.org/W3163091219","https://openalex.org/W3163157357","https://openalex.org/W3204087964","https://openalex.org/W4221162872","https://openalex.org/W4223460604","https://openalex.org/W4285144065","https://openalex.org/W4289752563","https://openalex.org/W4306964103","https://openalex.org/W4312402009","https://openalex.org/W4360764856","https://openalex.org/W4378473477","https://openalex.org/W4378977092","https://openalex.org/W4388550092","https://openalex.org/W4389687998","https://openalex.org/W4396855649","https://openalex.org/W6783670222"],"related_works":["https://openalex.org/W3095152779","https://openalex.org/W3119773509","https://openalex.org/W3128220219","https://openalex.org/W2990982991","https://openalex.org/W4323060069","https://openalex.org/W4317383455","https://openalex.org/W2997424368","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940"],"abstract_inverted_index":{"Recognizing":[0],"emotional":[1,99],"states":[2],"from":[3],"speech":[4,18],"is":[5,11,118,141],"essential":[6],"for":[7,43],"human-computer":[8],"interaction.":[9],"It":[10],"a":[12,36,64,103,132,190],"challenging":[13],"task":[14],"to":[15,56,95,119,143,150,167],"realize":[16,57],"effective":[17,58],"emotion":[19],"recognition":[20],"(SER)":[21],"on":[22,121,161,210],"platforms":[23],"with":[24,90,177],"limited":[25],"memory":[26],"capacity":[27],"and":[28,77,83,108,126,138,164,175,196,206],"computing":[29],"power.":[30,155],"In":[31,54],"this":[32],"paper,":[33],"we":[34,62,101],"propose":[35,63,102],"lightweight":[37],"multi-scale":[38,59,87],"deep":[39],"neural":[40],"network":[41],"architecture":[42],"SER,":[44],"which":[45],"takes":[46],"Mel":[47],"Frequency":[48],"Cepstral":[49],"Coefficients":[50],"(MFCCs)":[51],"as":[52,149],"input.":[53],"order":[55],"feature":[60],"extraction,":[61],"new":[65,104],"Inception":[66,75],"module,":[67],"named":[68],"A_Inception.":[69],"A_Inception":[70],"combines":[71],"the":[72,122,127,145,152,169,172,178,186],"merits":[73],"of":[74,115,171,193],"module":[76,117],"attention-based":[78],"rectified":[79],"linear":[80],"units":[81],"(AReLU)":[82],"thus":[84],"can":[85],"learn":[86],"features":[88],"adaptively":[89],"low":[91],"computational":[92,199],"cost.":[93],"Meanwhile,":[94],"extract":[96],"most":[97],"important":[98],"information,":[100],"multiscale":[105],"cepstral":[106,124],"attention":[107,110],"temporal-cepstral":[109,129],"(MCA-TCA)":[111],"module.":[112],"The":[113],"idea":[114],"MCA-TCA":[116],"focus":[120],"key":[123,128],"components":[125],"positions.":[130],"Furthermore,":[131],"loss":[133,137,140],"function":[134],"combining":[135],"Softmax":[136],"Center":[139],"adopted":[142],"supervise":[144],"model":[146,174,188],"training":[147],"so":[148],"enhance":[151],"model\u2019s":[153],"discriminative":[154],"Experiments":[156],"have":[157],"been":[158],"carried":[159],"out":[160],"IEMOCAP,":[162],"EMODB":[163],"SAVEE":[165],"datasets":[166,212],"verify":[168],"performance":[170],"proposed":[173,187],"compare":[176],"state-of-the-art":[179],"SER":[180],"models.":[181],"Numerical":[182],"results":[183],"reveal":[184],"that":[185],"has":[189],"small":[191],"number":[192],"parameters":[194],"(0.82M)":[195],"much":[197],"lower":[198],"cost":[200],"(81.64":[201],"MFLOPs)":[202],"than":[203],"compared":[204],"models,":[205],"achieves":[207],"impressive":[208],"accuracy":[209],"all":[211],"considered.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}