{"id":"https://openalex.org/W4385488508","doi":"https://doi.org/10.1109/ijcnn54540.2023.10192031","title":"Speech Emotion Recognition Using Dual Global Context Attention and Time-Frequency Features","display_name":"Speech Emotion Recognition Using Dual Global Context Attention and Time-Frequency Features","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488508","doi":"https://doi.org/10.1109/ijcnn54540.2023.10192031"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10192031","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10192031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003677173","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0002-9211-6582"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Qilu University of Technology,Shandong Computer Science Center,Jinan,China","Shandong Computer Science Center, Qilu University of Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology,Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853"]},{"raw_affiliation_string":"Shandong Computer Science Center, Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106172631","display_name":"Xuheng Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuheng Bai","raw_affiliation_strings":["Qilu University of Technology,Shandong Computer Science Center,Jinan,China","Shandong Computer Science Center, Qilu University of Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology,Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853"]},{"raw_affiliation_string":"Shandong Computer Science Center, Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102558786","display_name":"Jing Zhao","orcid":"https://orcid.org/0009-0001-1602-7510"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhao","raw_affiliation_strings":["Qilu University of Technology,Shandong Computer Science Center,Jinan,China","Shandong Computer Science Center, Qilu University of Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology,Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853"]},{"raw_affiliation_string":"Shandong Computer Science Center, Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101721116","display_name":"Yan Liang","orcid":"https://orcid.org/0000-0003-4596-587X"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Liang","raw_affiliation_strings":["Qilu University of Technology,Shandong Computer Science Center,Jinan,China","Shandong Computer Science Center, Qilu University of Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology,Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853"]},{"raw_affiliation_string":"Shandong Computer Science Center, Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100723485","display_name":"Fuqiang Wang","orcid":"https://orcid.org/0000-0002-7777-3541"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuqiang Wang","raw_affiliation_strings":["Qilu University of Technology,Shandong Computer Science Center,Jinan,China","Shandong Computer Science Center, Qilu University of Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology,Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853"]},{"raw_affiliation_string":"Shandong Computer Science Center, Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101981128","display_name":"Xiao-Ming Wu","orcid":"https://orcid.org/0000-0002-3130-0554"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Wu","raw_affiliation_strings":["Qilu University of Technology,Shandong Computer Science Center,Jinan,China","Shandong Computer Science Center, Qilu University of Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology,Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853"]},{"raw_affiliation_string":"Shandong Computer Science Center, Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I152269853"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I152269853"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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/T13289","display_name":"Infant Health and Development","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8409562706947327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7919610738754272},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6549716591835022},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6127845048904419},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5949201583862305},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5365325212478638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5141665935516357},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4861607253551483},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4233488440513611},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42297613620758057},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09433427453041077}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8409562706947327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919610738754272},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6549716591835022},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6127845048904419},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5949201583862305},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5365325212478638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5141665935516357},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4861607253551483},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4233488440513611},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42297613620758057},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09433427453041077},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10192031","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10192031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1542637018","https://openalex.org/W2055911634","https://openalex.org/W2074788634","https://openalex.org/W2146334809","https://openalex.org/W2803193013","https://openalex.org/W2885005742","https://openalex.org/W2889374687","https://openalex.org/W2964370293","https://openalex.org/W2967804986","https://openalex.org/W2972498864","https://openalex.org/W2982220924","https://openalex.org/W2992341299","https://openalex.org/W3008039831","https://openalex.org/W3015240477","https://openalex.org/W3015267357","https://openalex.org/W3015969913","https://openalex.org/W3022013598","https://openalex.org/W3039027785","https://openalex.org/W3134450397","https://openalex.org/W3139270985","https://openalex.org/W3159124063","https://openalex.org/W3162589478","https://openalex.org/W3163157357","https://openalex.org/W3197642003","https://openalex.org/W3209572141","https://openalex.org/W3213879871","https://openalex.org/W4205383840","https://openalex.org/W4220914964","https://openalex.org/W4225319211","https://openalex.org/W4226425326","https://openalex.org/W4285106979","https://openalex.org/W4297841699","https://openalex.org/W4303649252","https://openalex.org/W4312402009","https://openalex.org/W4312724610"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W1923358586","https://openalex.org/W2184242386","https://openalex.org/W2325729322","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,50],"recognition":[2,51,142],"(SER)":[3],"has":[4],"become":[5],"an":[6],"important":[7],"part":[8],"of":[9,15,34,72,121,144],"human-computer":[10],"interaction.":[11],"With":[12],"the":[13,21,31,88,101,107,111,119,150],"help":[14],"deep":[16],"learning":[17],"methods":[18],"such":[19],"as":[20,95,97],"attention":[22,58],"mechanism,":[23],"improved":[24],"performance":[25,135],"is":[26,84,136,161,165],"achieved":[27],"for":[28,167],"SER.":[29],"However,":[30],"emotional":[32],"features":[33,65,123],"speech":[35,49,73],"are":[36,66],"still":[37],"not":[38],"fully":[39],"extracted":[40,67],"and":[41,60,104,116,147,154],"utilized.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"propose":[47],"a":[48,80,98],"model":[52,140,159],"based":[53],"on":[54,149],"dual":[55,81],"global":[56,126],"context":[57,127],"(GCA)":[59],"time-frequency":[61,64],"features.":[62,90],"First,":[63],"from":[68],"3D":[69],"Log-Mel":[70],"spectrograms":[71],"using":[74],"parallel":[75],"2D":[76],"CNN":[77],"s.":[78],"Then,":[79],"GCA":[82,93],"architecture":[83],"designed":[85],"to":[86,124],"analyze":[87],"high-level":[89,102,122],"The":[91,138,158],"first":[92],"block,":[94],"well":[96],"CNN,":[99],"learns":[100],"temporal":[103],"spectral":[105],"features;":[106],"second":[108],"one":[109],"discovers":[110],"correlation":[112],"between":[113],"network":[114],"layers,":[115],"further":[117],"analyzes":[118],"fusion":[120],"obtain":[125],"information.":[128],"Experimental":[129],"results":[130],"show":[131],"that":[132],"competitive":[133],"SER":[134,168],"obtained.":[137],"proposed":[139],"achieves":[141],"accuracies":[143],"70.08%,":[145],"86.67%":[146],"93.27%":[148],"IEMOCAP,":[151],"RA":[152],"VDESS":[153],"EMO-DB":[155],"datasets,":[156],"respectively.":[157],"size":[160],"only":[162],"0.45M,":[163],"which":[164],"small":[166],"tasks.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}