{"id":"https://openalex.org/W4381802061","doi":"https://doi.org/10.1109/access.2023.3288526","title":"SCQT-MaxViT: Speech Emotion Recognition With Constant-Q Transform and Multi-Axis Vision Transformer","display_name":"SCQT-MaxViT: Speech Emotion Recognition With Constant-Q Transform and Multi-Axis Vision Transformer","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4381802061","doi":"https://doi.org/10.1109/access.2023.3288526"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3288526","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3288526","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10159377.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/ielx7/6287639/10005208/10159377.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012075531","display_name":"Kah Liang Ong","orcid":"https://orcid.org/0000-0001-9732-0067"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Kah Liang Ong","raw_affiliation_strings":["Faculty of Information Science and Technology, Multimedia University, Malacca, Malaysia"],"raw_orcid":"https://orcid.org/0000-0001-9732-0067","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Multimedia University, Malacca, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086127398","display_name":"Chin Poo Lee","orcid":"https://orcid.org/0000-0003-3679-8977"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Chin Poo Lee","raw_affiliation_strings":["Faculty of Information Science and Technology, Multimedia University, Malacca, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-3679-8977","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Multimedia University, Malacca, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062260573","display_name":"Heng Siong Lim","orcid":"https://orcid.org/0000-0002-8346-6345"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Heng Siong Lim","raw_affiliation_strings":["Faculty of Engineering and Technology, Multimedia University, Malacca, Malaysia"],"raw_orcid":"https://orcid.org/0000-0002-8346-6345","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Technology, Multimedia University, Malacca, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017532046","display_name":"Kian Ming Lim","orcid":"https://orcid.org/0000-0003-1929-7978"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Kian Ming Lim","raw_affiliation_strings":["Faculty of Information Science and Technology, Multimedia University, Malacca, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-1929-7978","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Multimedia University, Malacca, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092248142","display_name":"Takeki Mukaida","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeki Mukaida","raw_affiliation_strings":["School of Informatics and Engineering, University of Electro-Communications, Tokyo, Chofu, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Engineering, University of Electro-Communications, Tokyo, Chofu, Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":4.9503,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95609474,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"63081","last_page":"63091"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9900000095367432,"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":0.7993134260177612},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7688443660736084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6520588397979736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5621041655540466},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4665652811527252},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43199974298477173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993134260177612},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7688443660736084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6520588397979736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5621041655540466},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4665652811527252},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43199974298477173}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2023.3288526","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3288526","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10159377.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:shdl.mmu.edu.my:11588","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196753","display_name":"Siti Hasmah Digital Library-MMU Institutiona Repository (Multimedia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173029219","host_organization_name":"Multimedia University","host_organization_lineage":["https://openalex.org/I173029219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"},{"id":"pmh:oai:doaj.org/article:b566c276e9ac4e459962e27b09f70572","is_oa":true,"landing_page_url":"https://doaj.org/article/b566c276e9ac4e459962e27b09f70572","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 63081-63091 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3288526","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3288526","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10159377.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":[{"score":0.5,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3641693691","display_name":null,"funder_award_id":"RDTC/231084","funder_id":"https://openalex.org/F4320326578","funder_display_name":"Telekom Malaysia Berhad"},{"id":"https://openalex.org/G928522197","display_name":null,"funder_award_id":"FRGS/1/2021/ICT02/MMU/02/4","funder_id":"https://openalex.org/F4320321709","funder_display_name":"Ministry of Higher Education, Malaysia"}],"funders":[{"id":"https://openalex.org/F4320321709","display_name":"Ministry of Higher Education, Malaysia","ror":"https://ror.org/05mcs2t73"},{"id":"https://openalex.org/F4320326578","display_name":"Telekom Malaysia Berhad","ror":"https://ror.org/00s3fdw25"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381802061.pdf","grobid_xml":"https://content.openalex.org/works/W4381802061.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W2146334809","https://openalex.org/W2766272105","https://openalex.org/W2803193013","https://openalex.org/W2936451900","https://openalex.org/W2951123823","https://openalex.org/W2959133507","https://openalex.org/W2972640480","https://openalex.org/W2994791944","https://openalex.org/W3013363049","https://openalex.org/W3088789516","https://openalex.org/W3129285739","https://openalex.org/W3145643603","https://openalex.org/W3171087525","https://openalex.org/W3208052376","https://openalex.org/W4210796791","https://openalex.org/W4309564859","https://openalex.org/W4312847199","https://openalex.org/W4316659623","https://openalex.org/W4324382619","https://openalex.org/W4361731443","https://openalex.org/W4362579608","https://openalex.org/W6796931752"],"related_works":["https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,59],"recognition":[2],"presents":[3],"a":[4,115],"significant":[5],"challenge":[6],"within":[7,125],"the":[8,14,42,73,88,96,110,126,130,133,140,151,159,164,170,173],"field":[9],"of":[10,18,45,109,132,156],"affective":[11],"computing,":[12],"requiring":[13],"analysis":[15],"and":[16,34,66,86,107,122,128,167,182],"detection":[17],"emotions":[19,184],"conveyed":[20],"through":[21],"speech":[22,58,79,186],"signals.":[23,187],"However,":[24],"existing":[25],"approaches":[26],"often":[27],"rely":[28],"on":[29,158,163,169],"traditional":[30],"signal":[31,62],"processing":[32],"techniques":[33,148],"handcrafted":[35],"features,":[36],"which":[37],"may":[38],"not":[39],"effectively":[40],"capture":[41,91],"nuanced":[43],"aspects":[44],"emotional":[46,93],"expression.":[47],"In":[48],"this":[49],"paper,":[50],"an":[51],"approach":[52],"named":[53],"\u201cSCQT-MaxViT\u201d":[54],"is":[55,101,142],"proposed":[56,174],"for":[57,103],"recognition,":[60],"combining":[61],"processing,":[63],"computer":[64],"vision,":[65],"deep":[67],"learning":[68,106],"techniques.":[69],"The":[70],"method":[71,176],"utilizes":[72],"Constant-Q":[74],"Transform":[75],"(CQT)":[76],"to":[77,90,135,149],"convert":[78],"waveforms":[80],"into":[81],"spectrograms,":[82],"providing":[83],"high-frequency":[84],"resolution":[85],"enabling":[87],"model":[89,134],"intricate":[92],"details.":[94],"Additionally,":[95],"Multi-axis":[97],"Vision":[98],"Transformer":[99],"(MaxViT)":[100],"employed":[102],"further":[104],"representation":[105],"classification":[108],"CQT":[111],"spectrograms.":[112],"MaxViT":[113],"incorporates":[114],"multi-axis":[116],"self-attention":[117],"mechanism,":[118],"facilitating":[119],"both":[120],"local":[121],"global":[123],"interactions":[124],"network":[127],"enhancing":[129],"ability":[131],"learn":[136],"meaningful":[137],"features.":[138],"Furthermore,":[139],"dataset":[141],"augmented":[143],"using":[144],"random":[145],"time":[146],"masking":[147],"enhance":[150],"generalization":[152],"capabilities.":[153],"Achieving":[154],"accuracies":[155],"88.68%":[157],"Emo-DB":[160],"dataset,":[161,166,172],"77.54%":[162],"RAVDESS":[165],"62.49%":[168],"IEMOCAP":[171],"SCQT-MaxViT":[175],"exhibits":[177],"promising":[178],"performance":[179],"in":[180,185],"capturing":[181],"recognizing":[183]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}
