{"id":"https://openalex.org/W3157935640","doi":"https://doi.org/10.1109/icpr48806.2021.9412360","title":"The Application of Capsule Neural Network Based CNN for Speech Emotion Recognition","display_name":"The Application of Capsule Neural Network Based CNN for Speech Emotion Recognition","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3157935640","doi":"https://doi.org/10.1109/icpr48806.2021.9412360","mag":"3157935640"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5047620514","display_name":"Xin-Cheng Wen","orcid":"https://orcid.org/0000-0002-2115-9921"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin-Cheng Wen","raw_affiliation_strings":["School of Informatics, Xiamen University,Xiamen,China","School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066879706","display_name":"Kunhong Liu","orcid":"https://orcid.org/0000-0002-1222-8876"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun-Hong Liu","raw_affiliation_strings":["School of Informatics, Xiamen University,Xiamen,China","School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067689180","display_name":"Weiming Zhang","orcid":"https://orcid.org/0000-0001-5576-6108"},"institutions":[{"id":"https://openalex.org/I4210134189","display_name":"Xiamen University Malaysia","ror":"https://ror.org/0331wa828","country_code":"MY","type":"education","lineage":["https://openalex.org/I191208505","https://openalex.org/I4210134189"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Wei-Ming Zhang","raw_affiliation_strings":["School of Electrical and Computing Engineering, Xiamen university,Malaysia","School of Electrical and Computing Engineering, Xiamen university, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computing Engineering, Xiamen university,Malaysia","institution_ids":["https://openalex.org/I4210134189"]},{"raw_affiliation_string":"School of Electrical and Computing Engineering, Xiamen university, Malaysia","institution_ids":["https://openalex.org/I4210134189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101621263","display_name":"Kai Jiang","orcid":"https://orcid.org/0009-0005-3003-1881"},"institutions":[{"id":"https://openalex.org/I4210134189","display_name":"Xiamen University Malaysia","ror":"https://ror.org/0331wa828","country_code":"MY","type":"education","lineage":["https://openalex.org/I191208505","https://openalex.org/I4210134189"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Kai Jiang","raw_affiliation_strings":["School of Electrical and Computing Engineering, Xiamen university,Malaysia","School of Electrical and Computing Engineering, Xiamen university, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computing Engineering, Xiamen university,Malaysia","institution_ids":["https://openalex.org/I4210134189"]},{"raw_affiliation_string":"School of Electrical and Computing Engineering, Xiamen university, Malaysia","institution_ids":["https://openalex.org/I4210134189"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047620514"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":1.9283,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85317507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9356","last_page":"9362"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9965999722480774,"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/T11309","display_name":"Music and Audio Processing","score":0.9918000102043152,"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":0.8388698697090149},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6668555736541748},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.65607750415802},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6496096253395081},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6256851553916931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5538540482521057},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5066516995429993},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47212085127830505},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46230876445770264},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4619949162006378},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4405028820037842},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.42207399010658264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8388698697090149},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6668555736541748},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.65607750415802},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6496096253395081},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6256851553916931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5538540482521057},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5066516995429993},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47212085127830505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46230876445770264},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4619949162006378},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4405028820037842},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.42207399010658264},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G6187246181","display_name":null,"funder_award_id":"61772023","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1517164593","https://openalex.org/W1686810756","https://openalex.org/W1970976965","https://openalex.org/W1988111866","https://openalex.org/W2023937851","https://openalex.org/W2058819080","https://openalex.org/W2061068689","https://openalex.org/W2074788634","https://openalex.org/W2102548748","https://openalex.org/W2284361882","https://openalex.org/W2399733683","https://openalex.org/W2542587589","https://openalex.org/W2610961739","https://openalex.org/W2803098682","https://openalex.org/W2889717020","https://openalex.org/W2889943009","https://openalex.org/W2919115771","https://openalex.org/W2963703618","https://openalex.org/W2964113820","https://openalex.org/W3006565055","https://openalex.org/W6637373629","https://openalex.org/W6743446608"],"related_works":["https://openalex.org/W4296209631","https://openalex.org/W2045155990","https://openalex.org/W2561617217","https://openalex.org/W4313163053","https://openalex.org/W2025378473","https://openalex.org/W4300973204","https://openalex.org/W3045811229","https://openalex.org/W1483408780","https://openalex.org/W2355801475","https://openalex.org/W4284884309"],"abstract_inverted_index":{"Speech":[0],"emotion":[1],"recognition":[2],"(SER)":[3],"is":[4,105],"an":[5],"important":[6],"and":[7,22,74,96,128],"challenging":[8],"task.":[9,114],"It":[10],"requires":[11],"that":[12,67,88,107,135],"a":[13,18,65,69,75,91],"machine":[14],"learning":[15],"model":[16,66],"process":[17],"person's":[19],"speech":[20],"signals":[21],"to":[23,30,53],"judge":[24],"his":[25],"emotional":[26],"state":[27],"accurately.":[28],"Due":[29],"the":[31,35,38,45,56,98,112,126],"high":[32,123],"dimensionality":[33],"of":[34,47,84],"audio":[36,48,60],"data,":[37],"extracted":[39],"features":[40,49],"are":[41],"always":[42],"noisy.":[43],"Besides,":[44],"abstraction":[46],"makes":[50],"it":[51,89,104],"impossible":[52],"fully":[54],"use":[55],"inherent":[57],"relationship":[58],"among":[59],"features.":[61],"This":[62],"paper":[63],"proposes":[64],"combines":[68],"convolutional":[70],"neural":[71],"network":[72,77],"(CNN)":[73],"capsule":[76],"(CapsNet),":[78],"named":[79],"as":[80],"CapCNN.":[81],"The":[82,131],"advantage":[83],"CapCNN":[85,108],"lies":[86],"in":[87],"provides":[90,138],"solution":[92],"for":[93],"time":[94],"sensitivity,":[95],"gives":[97],"overall":[99],"characteristics.":[100],"In":[101],"this":[102],"study,":[103],"found":[106],"can":[109],"well":[110],"handle":[111],"SER":[113],"Compared":[115],"with":[116],"other":[117],"state-of-the-art":[118],"methods,":[119],"our":[120,136],"algorithm":[121],"shows":[122],"performances":[124],"on":[125,141],"CASIA":[127],"EMODB":[129],"datasets.":[130],"detailed":[132],"analysis":[133],"confirms":[134],"method":[137],"balanced":[139],"results":[140],"various":[142],"classes.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}