{"id":"https://openalex.org/W3205428167","doi":"https://doi.org/10.1109/taslp.2021.3120586","title":"Speech Emotion Recognition Using Sequential Capsule Networks","display_name":"Speech Emotion Recognition Using Sequential Capsule Networks","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3205428167","doi":"https://doi.org/10.1109/taslp.2021.3120586","mag":"3205428167"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3120586","doi":"https://doi.org/10.1109/taslp.2021.3120586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3120586","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"volume":null,"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/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572","observed_orcids":["https://orcid.org/0000-0001-9543-1572"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["[Stanley Ho Big Data Decision Analytics Research Centre, The Chinese University of Hong Kong, Hong Kong, China]"],"raw_orcid":"https://orcid.org/0000-0001-9543-1572","affiliations":[{"raw_affiliation_string":"[Stanley Ho Big Data Decision Analytics Research Centre, The Chinese University of Hong Kong, Hong Kong, China]","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013296368","display_name":"Yuewen Cao","orcid":"https://orcid.org/0000-0002-1432-161X","observed_orcids":["https://orcid.org/0000-0002-1432-161X"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuewen Cao","raw_affiliation_strings":["Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-1432-161X","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101486499","display_name":"Hui Lu","orcid":"https://orcid.org/0000-0002-7698-6262","observed_orcids":["https://orcid.org/0000-0002-7698-6262"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hui Lu","raw_affiliation_strings":["Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102778496","display_name":"Songxiang Liu","orcid":"https://orcid.org/0000-0002-0943-2446","observed_orcids":["https://orcid.org/0000-0002-0943-2446"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Songxiang Liu","raw_affiliation_strings":["Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-0943-2446","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068726270","display_name":"Disong Wang","orcid":"https://orcid.org/0000-0001-8481-6880","observed_orcids":["https://orcid.org/0000-0001-8481-6880"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Disong Wang","raw_affiliation_strings":["Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-8481-6880","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524","observed_orcids":["https://orcid.org/0000-0001-8533-0524"]},"institutions":[{"id":"https://openalex.org/I4405263052","display_name":"Tsinghua Shenzhen International Graduate School","ror":"https://ror.org/01vceef04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8533-0524","affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University Shenzhen, China","institution_ids":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160","observed_orcids":["https://orcid.org/0000-0001-6725-1160"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-6725-1160","affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen M. L. Meng","orcid":"https://orcid.org/0000-0002-4427-3532","observed_orcids":["https://orcid.org/0000-0002-4427-3532"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Mangement, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":6.7661,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.96896175,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"3280","last_page":"3291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9911999702453613,"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":0.9911999702453613,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.006399999838322401,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10860","display_name":"Speech and Audio Processing","score":0.0010999999940395355,"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/speech-emotion-recognition","display_name":"speech emotion recognition","score":1.0},{"id":"https://openalex.org/keywords/dynamic-routing","display_name":"dynamic routing","score":0.9430000185966492},{"id":"https://openalex.org/keywords/spatial-information-preservation","display_name":"spatial information preservation","score":0.7760000228881836},{"id":"https://openalex.org/keywords/spectrogram-features","display_name":"spectrogram features","score":0.6230000257492065},{"id":"https://openalex.org/keywords/recurrent-connections","display_name":"recurrent connectivity","score":0.675000011920929},{"id":"https://openalex.org/keywords/utterance-level-features","display_name":"utterance-level features","score":0.847000002861023},{"id":"https://openalex.org/keywords/contextual-information","display_name":"contextual information","score":0.7829999923706055},{"id":"https://openalex.org/keywords/iemocap","display_name":"IEMOCAP","score":0.8870000243186951}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6384001970291138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46335461735725403},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.38710641860961914},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.378131628036499}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3120586","doi":"https://doi.org/10.1109/taslp.2021.3120586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3120586","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"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":54,"referenced_works":["https://openalex.org/W2966661","https://openalex.org/W1522301498","https://openalex.org/W1987048275","https://openalex.org/W1989639247","https://openalex.org/W1994458317","https://openalex.org/W2062391442","https://openalex.org/W2074788634","https://openalex.org/W2110052520","https://openalex.org/W2146334809","https://openalex.org/W2161459043","https://openalex.org/W2250999640","https://openalex.org/W2295001676","https://openalex.org/W2296073425","https://openalex.org/W2408520939","https://openalex.org/W2567070169","https://openalex.org/W2578895956","https://openalex.org/W2591183831","https://openalex.org/W2625297138","https://openalex.org/W2648194195","https://openalex.org/W2740046088","https://openalex.org/W2746978487","https://openalex.org/W2747664154","https://openalex.org/W2751777443","https://openalex.org/W2752386593","https://openalex.org/W2761514455","https://openalex.org/W2785994986","https://openalex.org/W2800253600","https://openalex.org/W2889018940","https://openalex.org/W2889107526","https://openalex.org/W2889191742","https://openalex.org/W2889374687","https://openalex.org/W2889411717","https://openalex.org/W2889507358","https://openalex.org/W2889544113","https://openalex.org/W2897403446","https://openalex.org/W2900974431","https://openalex.org/W2926516160","https://openalex.org/W2936113082","https://openalex.org/W2936372954","https://openalex.org/W2944004378","https://openalex.org/W2951123823","https://openalex.org/W2959546144","https://openalex.org/W2962853356","https://openalex.org/W2963467407","https://openalex.org/W2963970792","https://openalex.org/W2964121744","https://openalex.org/W2964168600","https://openalex.org/W2964233791","https://openalex.org/W2972811324","https://openalex.org/W2990253095","https://openalex.org/W3012640291","https://openalex.org/W3015240477","https://openalex.org/W3015267357","https://openalex.org/W4301204483"],"related_works":["https://openalex.org/W2936113082","https://openalex.org/W3157935640","https://openalex.org/W4385951156","https://openalex.org/W7127387313","https://openalex.org/W7213425494","https://openalex.org/W3195507353","https://openalex.org/W3212444814","https://openalex.org/W4285308079","https://openalex.org/W4214949954","https://openalex.org/W4318355338"],"abstract_inverted_index":{"Speech":[0],"emotion":[1],"recognition":[2],"(SER)":[3],"is":[4,42,49],"an":[5,105],"indispensable":[6],"part":[7],"of":[8,15,40,57,71,80,146,169],"fluid":[9],"human-machine":[10],"interaction":[11],"and":[12,54,63,90,150,156],"attracts":[13],"lots":[14],"research":[16],"attentions.":[17],"Recent":[18],"work":[19],"on":[20,162],"SER":[21],"has":[22],"successfully":[23],"applied":[24],"convolutional":[25],"neural":[26,158],"networks":[27,74,159],"(CNNs)":[28],"to":[29,92,108,130,139],"learn":[30],"feature":[31],"representations":[32],"from":[33,119],"speech":[34],"spectrograms.":[35],"However,":[36],"the":[37,44,78,100,120,127,140,147,163,167,170],"fundamental":[38],"problem":[39],"CNNs":[41,155],"that":[43,82],"spatial":[45,83],"information":[46,56,84],"in":[47,88],"spectrograms":[48],"lost,":[50],"which":[51],"includes":[52],"positional":[53],"relationship":[55],"low-level":[58],"features,":[59],"such":[60],"as":[61],"pitch":[62],"formant":[64],"frequencies.":[65],"We":[66],"propose":[67],"a":[68,136],"novel":[69],"architecture":[70],"sequential":[72,121,141,172],"capsule":[73,94,122],"(CapNets)":[75],"by":[76],"leveraging":[77],"advantange":[79],"CapNets":[81],"can":[85],"be":[86],"preserved":[87],"capsules":[89],"passed":[91],"upper":[93],"layers":[95],"via":[96],"dynamic":[97,101],"routing.":[98],"Also,":[99],"routing":[102],"algorithm":[103],"provides":[104],"effective":[106],"alternative":[107],"pooling":[109],"or":[110],"storing":[111],"recurrent":[112,137,157],"hidden":[113],"states":[114],"for":[115],"obtaining":[116],"utterance-level":[117],"features":[118],"outputs.":[123],"To":[124],"further":[125],"improve":[126],"model's":[128],"ability":[129],"capture":[131],"contextual":[132],"information,":[133],"we":[134],"introduce":[135],"connection":[138],"structure.":[142],"The":[143],"experimental":[144],"comparison":[145],"proposed":[148,171],"systems":[149,153],"previously":[151],"published":[152],"using":[154],"(RNNs)":[160],"based":[161],"IEMOCAP":[164],"corpus":[165],"demonstrates":[166],"effectiveness":[168],"CapNets.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-10-25T00:00:00"}