{"id":"https://openalex.org/W3107569919","doi":"https://doi.org/10.3390/s20226688","title":"Fusion-ConvBERT: Parallel Convolution and BERT Fusion for Speech Emotion Recognition","display_name":"Fusion-ConvBERT: Parallel Convolution and BERT Fusion for Speech Emotion Recognition","publication_year":2020,"publication_date":"2020-11-23","ids":{"openalex":"https://openalex.org/W3107569919","doi":"https://doi.org/10.3390/s20226688","mag":"3107569919","pmid":"https://pubmed.ncbi.nlm.nih.gov/33238396"},"language":"en","primary_location":{"id":"doi:10.3390/s20226688","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s20226688","pdf_url":"https://www.mdpi.com/1424-8220/20/22/6688/pdf?version=1606115493","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/20/22/6688/pdf?version=1606115493","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100444551","display_name":"Sanghyun Lee","orcid":"https://orcid.org/0000-0002-1107-0122"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghyun Lee","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Korea University, Seoul 136-713, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Korea University, Seoul 136-713, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102000970","display_name":"David K. Han","orcid":"https://orcid.org/0000-0001-5055-5408"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David K. Han","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026204977","display_name":"Hanseok Ko","orcid":"https://orcid.org/0000-0002-8744-4514"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hanseok Ko","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Korea University, Seoul 136-713, Korea"],"raw_orcid":"https://orcid.org/0000-0002-8744-4514","affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Korea University, Seoul 136-713, Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5026204977"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":3.3126,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.92503142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"20","issue":"22","first_page":"6688","last_page":"6688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980000257492065,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7745254039764404},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6768860816955566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6174817681312561},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6002455353736877},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5807217359542847},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5644510984420776},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.45250096917152405},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41880717873573303},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41035908460617065},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4102192521095276},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36627405881881714}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7745254039764404},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6768860816955566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6174817681312561},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6002455353736877},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5807217359542847},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5644510984420776},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.45250096917152405},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41880717873573303},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41035908460617065},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4102192521095276},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36627405881881714},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s20226688","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s20226688","pdf_url":"https://www.mdpi.com/1424-8220/20/22/6688/pdf?version=1606115493","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:33238396","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33238396","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:37e5f2862a00489988eafe9d6c25cce6","is_oa":true,"landing_page_url":"https://doaj.org/article/37e5f2862a00489988eafe9d6c25cce6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 20, Iss 22, p 6688 (2020)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/20/22/6688/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s20226688","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 20; Issue 22; Pages: 6688","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:7700332","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7700332","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s20226688","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s20226688","pdf_url":"https://www.mdpi.com/1424-8220/20/22/6688/pdf?version=1606115493","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3107569919.pdf","grobid_xml":"https://content.openalex.org/works/W3107569919.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1494198834","https://openalex.org/W1753166931","https://openalex.org/W2000838212","https://openalex.org/W2009059481","https://openalex.org/W2037960784","https://openalex.org/W2038821742","https://openalex.org/W2055911634","https://openalex.org/W2074788634","https://openalex.org/W2087618018","https://openalex.org/W2095540482","https://openalex.org/W2095705004","https://openalex.org/W2099767163","https://openalex.org/W2110052520","https://openalex.org/W2111926505","https://openalex.org/W2113872551","https://openalex.org/W2119534679","https://openalex.org/W2140801466","https://openalex.org/W2145487065","https://openalex.org/W2146334809","https://openalex.org/W2181741066","https://openalex.org/W2191779130","https://openalex.org/W2280078499","https://openalex.org/W2280236323","https://openalex.org/W2399733683","https://openalex.org/W2515667479","https://openalex.org/W2578895956","https://openalex.org/W2592702372","https://openalex.org/W2625297138","https://openalex.org/W2625435062","https://openalex.org/W2626778328","https://openalex.org/W2738561771","https://openalex.org/W2765860599","https://openalex.org/W2766756589","https://openalex.org/W2786779322","https://openalex.org/W2787560479","https://openalex.org/W2803098682","https://openalex.org/W2885005742","https://openalex.org/W2888786729","https://openalex.org/W2909327627","https://openalex.org/W2936774411","https://openalex.org/W2939710050","https://openalex.org/W2951123823","https://openalex.org/W2951975883","https://openalex.org/W2955805055","https://openalex.org/W2959133507","https://openalex.org/W2961638199","https://openalex.org/W2962739339","https://openalex.org/W2963130397","https://openalex.org/W2963175699","https://openalex.org/W2963467407","https://openalex.org/W2970737019","https://openalex.org/W2973049979","https://openalex.org/W2973181312","https://openalex.org/W2982223350","https://openalex.org/W3015265920","https://openalex.org/W3037742886","https://openalex.org/W6674330103","https://openalex.org/W6695420137","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2369710579","https://openalex.org/W4327728159","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,61,92,169],"recognition":[2,30,93],"predicts":[3],"the":[4,12,42,54,58,79,91,126,156,160,176,185],"emotional":[5,29],"state":[6],"of":[7,44,60,141,184],"a":[8,109,112,136],"speaker":[9,72],"based":[10,34],"on":[11,28,35,155],"person's":[13],"speech.":[14],"It":[15],"brings":[16,75],"an":[17],"additional":[18],"element":[19],"for":[20,98,111],"creating":[21],"more":[22],"natural":[23],"human-computer":[24],"interactions.":[25],"Earlier":[26],"studies":[27],"have":[31,48],"been":[32,49],"primarily":[33],"handcrafted":[36],"features":[37,69],"and":[38,147,162,171],"manual":[39],"labels.":[40],"With":[41],"advent":[43],"deep":[45,64,101],"learning,":[46],"there":[47,107],"some":[50,85],"efforts":[51],"in":[52,87,182],"applying":[53,88],"deep-network-based":[55],"approach":[56,115],"to":[57,71,90,125],"problem":[59],"recognition.":[62],"As":[63],"learning":[65],"automatically":[66],"extracts":[67],"salient":[68],"correlated":[70],"emotion,":[73],"it":[74,172],"certain":[76],"advantages":[77],"over":[78],"handcrafted-feature-based":[80],"methods.":[81],"There":[82],"are,":[83],"however,":[84],"challenges":[86],"them":[89],"problem,":[94],"because":[95],"data":[96],"required":[97],"properly":[99],"training":[100],"networks":[102],"are":[103],"often":[104],"lacking.":[105],"Therefore,":[106],"is":[108,135],"need":[110],"new":[113],"deep-learning-based":[114],"which":[116],"can":[117],"exploit":[118],"available":[119],"information":[120],"from":[121,145],"given":[122],"speech":[123],"signals":[124],"maximum":[127],"extent":[128],"possible.":[129],"Our":[130],"proposed":[131,157,177],"method,":[132],"called":[133],"\"Fusion-ConvBERT\",":[134],"parallel":[137],"fusion":[138],"model":[139,158],"consisting":[140],"bidirectional":[142],"encoder":[143],"representations":[144],"transformers":[146],"convolutional":[148],"neural":[149],"networks.":[150],"Extensive":[151],"experiments":[152],"were":[153],"conducted":[154],"using":[159],"EMO-DB":[161],"Interactive":[163],"Emotional":[164],"Dyadic":[165],"Motion":[166],"Capture":[167],"Database":[168],"corpus,":[170],"was":[173],"shown":[174],"that":[175],"method":[178],"outperformed":[179],"state-of-the-art":[180],"techniques":[181],"most":[183],"test":[186],"configurations.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}