{"id":"https://openalex.org/W4379033883","doi":"https://doi.org/10.1109/taslp.2023.3282092","title":"Dual-TBNet: Improving the Robustness of Speech Features via Dual-Transformer-BiLSTM for Speech Emotion Recognition","display_name":"Dual-TBNet: Improving the Robustness of Speech Features via Dual-Transformer-BiLSTM for Speech Emotion Recognition","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4379033883","doi":"https://doi.org/10.1109/taslp.2023.3282092"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3282092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3282092","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,"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"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://tokushima-u.repo.nii.ac.jp/record/2011247/files/taslp_31_2193.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080065046","display_name":"Zheng Liu","orcid":"https://orcid.org/0000-0003-0685-1124"},"institutions":[{"id":"https://openalex.org/I922474255","display_name":"Tokushima University","ror":"https://ror.org/044vy1d05","country_code":"JP","type":"education","lineage":["https://openalex.org/I922474255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zheng Liu","raw_affiliation_strings":["Faculty of Science and Engineering, Tokushima University, Tokushima, Japan","Institute of Technology and Science, Tokushima University, Tokushima, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0685-1124","affiliations":[{"raw_affiliation_string":"Faculty of Science and Engineering, Tokushima University, Tokushima, Japan","institution_ids":["https://openalex.org/I922474255"]},{"raw_affiliation_string":"Institute of Technology and Science, Tokushima University, Tokushima, Japan","institution_ids":["https://openalex.org/I922474255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031861539","display_name":"Xin Kang","orcid":"https://orcid.org/0000-0001-6024-3598"},"institutions":[{"id":"https://openalex.org/I922474255","display_name":"Tokushima University","ror":"https://ror.org/044vy1d05","country_code":"JP","type":"education","lineage":["https://openalex.org/I922474255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Kang","raw_affiliation_strings":["Department of Information Science and Intelligent Systems, Tokushima University, Tokushima, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6024-3598","affiliations":[{"raw_affiliation_string":"Department of Information Science and Intelligent Systems, Tokushima University, Tokushima, Japan","institution_ids":["https://openalex.org/I922474255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071943346","display_name":"Fuji Ren","orcid":"https://orcid.org/0000-0003-4860-9184"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuji Ren","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-4860-9184","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.0979,"has_fulltext":true,"cited_by_count":64,"citation_normalized_percentile":{"value":0.99204569,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"2193","last_page":"2203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9986000061035156,"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":0.9961000084877014,"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":0.7900172472000122},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7329390048980713},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6175509095191956},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6130759119987488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5721499919891357},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5493561029434204},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.48371532559394836},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48321783542633057},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.47272342443466187},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.42716896533966064},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2600169777870178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900172472000122},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7329390048980713},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6175509095191956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6130759119987488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5721499919891357},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5493561029434204},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.48371532559394836},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48321783542633057},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.47272342443466187},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.42716896533966064},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2600169777870178},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2023.3282092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3282092","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,"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"},{"id":"pmh:oai:irdb.nii.ac.jp:00906:0006783074","is_oa":true,"landing_page_url":"https://tokushima-u.repo.nii.ac.jp/records/2011247","pdf_url":"https://tokushima-u.repo.nii.ac.jp/record/2011247/files/taslp_31_2193.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:00906:0006783074","is_oa":true,"landing_page_url":"https://tokushima-u.repo.nii.ac.jp/records/2011247","pdf_url":"https://tokushima-u.repo.nii.ac.jp/record/2011247/files/taslp_31_2193.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379033883.pdf","grobid_xml":"https://content.openalex.org/works/W4379033883.grobid-xml"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1885777359","https://openalex.org/W1996265292","https://openalex.org/W2090254175","https://openalex.org/W2146334809","https://openalex.org/W2396589722","https://openalex.org/W2771498260","https://openalex.org/W2784665486","https://openalex.org/W2785194761","https://openalex.org/W2885005742","https://openalex.org/W2889191349","https://openalex.org/W2914650326","https://openalex.org/W2968055463","https://openalex.org/W2972463723","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2981857663","https://openalex.org/W2982223350","https://openalex.org/W2995852188","https://openalex.org/W2997399314","https://openalex.org/W2997887270","https://openalex.org/W3007075806","https://openalex.org/W3008039831","https://openalex.org/W3012197804","https://openalex.org/W3014475539","https://openalex.org/W3016962243","https://openalex.org/W3020634498","https://openalex.org/W3035319255","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3043221004","https://openalex.org/W3082010634","https://openalex.org/W3085139254","https://openalex.org/W3092788858","https://openalex.org/W3095648847","https://openalex.org/W3096690837","https://openalex.org/W3100270690","https://openalex.org/W3102342027","https://openalex.org/W3117956262","https://openalex.org/W3119048198","https://openalex.org/W3126625480","https://openalex.org/W3129337289","https://openalex.org/W3132302778","https://openalex.org/W3133207760","https://openalex.org/W3138410940","https://openalex.org/W3139270985","https://openalex.org/W3144907487","https://openalex.org/W3145643603","https://openalex.org/W3148040514","https://openalex.org/W3159124063","https://openalex.org/W3173151551","https://openalex.org/W3198858531","https://openalex.org/W4206675400","https://openalex.org/W4206706211","https://openalex.org/W4212961154","https://openalex.org/W4230235222","https://openalex.org/W4285166852","https://openalex.org/W4288765755","https://openalex.org/W4297808394","https://openalex.org/W4312611743","https://openalex.org/W4312729513","https://openalex.org/W4385245566","https://openalex.org/W6712588427","https://openalex.org/W6739901393","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6784776607","https://openalex.org/W6797132756","https://openalex.org/W6811766668","https://openalex.org/W6844194202","https://openalex.org/W7028336066"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W4376166922","https://openalex.org/W2490526372","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Speech":[0],"emotion":[1],"recognition":[2,79,186],"has":[3],"always":[4],"been":[5],"one":[6],"of":[7,15,39,46,65,89,100,124,157,165,191,235,246],"the":[8,25,32,36,47,63,73,78,87,134,139,142,147,154,158,178,181,196,203,210,217,225,244,247,251],"topics":[9],"that":[10,98],"have":[11],"attracted":[12],"a":[13,94,163,185],"lot":[14],"attention":[16,135],"from":[17,31],"many":[18],"researchers.":[19],"In":[20,49,68,177],"traditional":[21],"feature":[22,95],"fusion":[23,96,167],"methods,":[24],"speech":[26,66,90],"features":[27,40,91,123,173,234],"used":[28],"only":[29],"come":[30],"data":[33],"set,":[34],"and":[35,76,92,108,128,145,174,188,193,200,207,214,220,222,238,249],"weak":[37],"robustness":[38,88,245],"can":[41],"easily":[42],"lead":[43],"to":[44,57,71,85,121,137,152,169],"overfitting":[45],"model.":[48],"addition,":[50],"these":[51],"methods":[52],"often":[53],"use":[54],"simple":[55],"concatenation":[56],"fuse":[58,170],"features,":[59,144,242,248],"which":[60],"will":[61],"cause":[62],"loss":[64],"information.":[67],"this":[69],"paper,":[70],"solve":[72],"above":[74],"problems":[75],"improve":[77],"accuracy,":[80],"we":[81],"utilize":[82],"self-supervised":[83],"learning":[84],"enhance":[86,153],"propose":[93],"model(Dual-TBNet)":[97],"consists":[99],"two":[101,105,109,143],"1D":[102,119],"convolutional":[103],"layers,":[104],"Transformer":[106],"modules":[107],"bidirectional":[110,148],"long":[111],"short-term":[112],"memory":[113],"(BiLSTM)":[114],"modules.":[115],"Our":[116],"model":[117,183,230],"uses":[118,133,146],"convolution":[120],"take":[122],"different":[125,236],"segment":[126],"lengths":[127,237],"dimension":[129],"sizes":[130],"as":[131],"input,":[132],"mechanism":[136],"capture":[138],"correspondence":[140],"between":[141],"time":[149],"series":[150],"module":[151],"contextual":[155],"information":[156],"fused":[159],"features.":[160,176],"We":[161],"designed":[162],"total":[164],"four":[166],"models":[168],"five":[171],"pre-trained":[172,241],"acoustic":[175,233],"comparison":[179],"experiments,":[180],"Dual-TBNet":[182,229],"achieved":[184,250],"accuracy":[187],"F1":[189],"score":[190],"95.7%":[192],"95.8%":[194],"on":[195,202,209,216,224],"CASIA":[197],"dataset,":[198,205,212],"66.7%":[199],"65.6%":[201],"eNTERFACE05":[204],"64.8%":[206],"64.9%":[208],"IEMOCAP":[211],"84.1%":[213],"84.3%":[215],"EMO-DB":[218],"dataset":[219],"83.3%":[221],"82.1%":[223],"SAVEE":[226],"dataset.":[227],"The":[228],"effectively":[231],"fuses":[232],"dimensions":[239],"with":[240],"enhancing":[243],"best":[252],"performance.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":24}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}