{"id":"https://openalex.org/W4323824557","doi":"https://doi.org/10.1109/iceic57457.2023.10049941","title":"CoordViT: A Novel Method of Improve Vision Transformer-Based Speech Emotion Recognition using Coordinate Information Concatenate","display_name":"CoordViT: A Novel Method of Improve Vision Transformer-Based Speech Emotion Recognition using Coordinate Information Concatenate","publication_year":2023,"publication_date":"2023-02-05","ids":{"openalex":"https://openalex.org/W4323824557","doi":"https://doi.org/10.1109/iceic57457.2023.10049941"},"language":"en","primary_location":{"id":"doi:10.1109/iceic57457.2023.10049941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic57457.2023.10049941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5002350462","display_name":"Jeong\u2010Yoon Kim","orcid":"https://orcid.org/0000-0001-5873-2069"},"institutions":[{"id":"https://openalex.org/I145808223","display_name":"Hanbat National University","ror":"https://ror.org/00x514t95","country_code":"KR","type":"education","lineage":["https://openalex.org/I145808223"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jeong-Yoon Kim","raw_affiliation_strings":["Hanbat National University,Dept. Electronic Engineering,Daejeon,Korea","Dept. Electronic Engineering, Hanbat National University, Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"Hanbat National University,Dept. Electronic Engineering,Daejeon,Korea","institution_ids":["https://openalex.org/I145808223"]},{"raw_affiliation_string":"Dept. Electronic Engineering, Hanbat National University, Daejeon, Korea","institution_ids":["https://openalex.org/I145808223"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100363404","display_name":"Seung-Ho Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I145808223","display_name":"Hanbat National University","ror":"https://ror.org/00x514t95","country_code":"KR","type":"education","lineage":["https://openalex.org/I145808223"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Ho Lee","raw_affiliation_strings":["Hanbat National University,Dept. Electronic Engineering,Daejeon,Korea","Dept. Electronic Engineering, Hanbat National University, Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"Hanbat National University,Dept. Electronic Engineering,Daejeon,Korea","institution_ids":["https://openalex.org/I145808223"]},{"raw_affiliation_string":"Dept. Electronic Engineering, Hanbat National University, Daejeon, Korea","institution_ids":["https://openalex.org/I145808223"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002350462"],"corresponding_institution_ids":["https://openalex.org/I145808223"],"apc_list":null,"apc_paid":null,"fwci":2.649,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90597809,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9959999918937683,"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/T11309","display_name":"Music and Audio Processing","score":0.9824000000953674,"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":0.7623556852340698},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7383919358253479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.653989315032959},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.553875744342804},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5423673987388611},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5233480334281921},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.508569598197937},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46743789315223694},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.46249961853027344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37947359681129456},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10060542821884155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623556852340698},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7383919358253479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.653989315032959},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.553875744342804},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5423673987388611},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5233480334281921},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.508569598197937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46743789315223694},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.46249961853027344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37947359681129456},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10060542821884155},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceic57457.2023.10049941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic57457.2023.10049941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2896457183","https://openalex.org/W2963623257","https://openalex.org/W2964121744","https://openalex.org/W3015356123","https://openalex.org/W3035264762","https://openalex.org/W3094502228","https://openalex.org/W3121523901","https://openalex.org/W3196974791","https://openalex.org/W3198908807","https://openalex.org/W4296068596","https://openalex.org/W4385245566","https://openalex.org/W4385876305","https://openalex.org/W6631190155","https://openalex.org/W6753441378","https://openalex.org/W6755207826","https://openalex.org/W6784333009","https://openalex.org/W6788135285"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W3179495260","https://openalex.org/W3127543252","https://openalex.org/W2119567889"],"abstract_inverted_index":{"Recently,":[0],"in":[1,45,62,122],"speech":[2,73],"emotion":[3,74],"recognition,":[4],"a":[5,26,43,67,112],"Transformer-based":[6,27],"method":[7,69,83],"using":[8,34,76],"spectrogram":[9],"images":[10],"instead":[11],"of":[12,70,98],"sound":[13],"data":[14],"showed":[15],"improved":[16,102],"accuracy":[17,32,97],"than":[18],"Convolutional":[19],"Neural":[20],"Networks":[21],"(CNNs).":[22],"Vision":[23],"Transformer":[24],"(ViT),":[25],"method,":[28],"achieves":[29],"high":[30],"classification":[31],"by":[33,88,103],"divided":[35],"patches":[36],"from":[37],"the":[38,81,93,96,107,117],"input":[39,94],"image,":[40,95],"but":[41,131],"has":[42],"problem":[44],"that":[46,116],"pixel":[47,85],"position":[48,86],"information":[49,78,87,91,119],"is":[50,100,125],"not":[51,127],"retained":[52],"due":[53],"to":[54,92,106],"embedding":[55],"layers":[56],"such":[57],"as":[58],"linear":[59],"projection.":[60],"Therefore,":[61],"this":[63,123],"paper,":[64],"we":[65],"propose":[66],"novel":[68],"improve":[71],"ViT-based":[72],"recognition":[75],"coordinate":[77,90,118],"concatenate.":[79],"Since":[80],"proposed":[82,121],"retains":[84],"concatenating":[89],"CREMA-D":[99],"greatly":[101],"82.96%":[104],"compared":[105],"state-of-art":[108],"about":[109],"CREMA-D.":[110],"As":[111],"result,":[113],"it":[114],"proved":[115],"concatenate":[120],"paper":[124],"effective":[126],"only":[128],"for":[129,133],"CNNs":[130],"also":[132],"Transformers.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}