{"id":"https://openalex.org/W2897191477","doi":"https://doi.org/10.1109/slt.2018.8639583","title":"Multimodal Speech Emotion Recognition Using Audio and Text","display_name":"Multimodal Speech Emotion Recognition Using Audio and Text","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2897191477","doi":"https://doi.org/10.1109/slt.2018.8639583","mag":"2897191477"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1810.04635","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101424021","display_name":"Seunghyun Yoon","orcid":"https://orcid.org/0000-0002-7262-3579"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seunghyun Yoon","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, Seoul National University, Seoul, Korea","Department of Electrical & Computer Engineering, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085168588","display_name":"Seokhyun Byun","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seokhyun Byun","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, Seoul National University, Seoul, Korea","Department of Electrical & Computer Engineering, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077832834","display_name":"Kyomin Jung","orcid":"https://orcid.org/0000-0003-2547-7051"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyomin Jung","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, Seoul National University, Seoul, Korea","Department of Electrical & Computer Engineering, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101424021"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.8765,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.78039873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"112","last_page":"118"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9990000128746033,"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":0.8024107217788696},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.70167076587677},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5836349129676819},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5491852164268494},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5447936058044434},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5435599684715271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4960859715938568},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4884135127067566},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4633999168872833},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4267244338989258},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42395660281181335},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4153135418891907},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31690022349357605},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31550732254981995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8024107217788696},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.70167076587677},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5836349129676819},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5491852164268494},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5447936058044434},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5435599684715271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4960859715938568},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4884135127067566},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4633999168872833},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4267244338989258},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42395660281181335},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4153135418891907},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31690022349357605},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31550732254981995},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt.2018.8639583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.04635","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.04635","pdf_url":"https://arxiv.org/pdf/1810.04635","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2897191477","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1810.04635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:s-space.snu.ac.kr:10371/186820","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/186820","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"doi:10.48550/arxiv.1810.04635","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1810.04635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.04635","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.04635","pdf_url":"https://arxiv.org/pdf/1810.04635","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1103364132","display_name":null,"funder_award_id":"10073144","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"},{"id":"https://openalex.org/G8582691448","display_name":null,"funder_award_id":"MOTIE, Korea","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"},{"id":"https://openalex.org/G992484961","display_name":null,"funder_award_id":"Korea","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"}],"funders":[{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2897191477.pdf","grobid_xml":"https://content.openalex.org/works/W2897191477.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W1924770834","https://openalex.org/W2000838212","https://openalex.org/W2090777335","https://openalex.org/W2110052520","https://openalex.org/W2125930537","https://openalex.org/W2127141656","https://openalex.org/W2140801466","https://openalex.org/W2143017621","https://openalex.org/W2146334809","https://openalex.org/W2153720647","https://openalex.org/W2193413348","https://openalex.org/W2250539671","https://openalex.org/W2295001676","https://openalex.org/W2407005679","https://openalex.org/W2408520939","https://openalex.org/W2550557083","https://openalex.org/W2598207902","https://openalex.org/W2625297138","https://openalex.org/W2648194195","https://openalex.org/W2696559478","https://openalex.org/W2707551695","https://openalex.org/W2747664154","https://openalex.org/W2749894918","https://openalex.org/W2805005636","https://openalex.org/W2949335953","https://openalex.org/W2962736520","https://openalex.org/W2963130397","https://openalex.org/W2964308564","https://openalex.org/W4245267204","https://openalex.org/W6640212811","https://openalex.org/W6676494506","https://openalex.org/W6678818196","https://openalex.org/W6679434410","https://openalex.org/W6684191040","https://openalex.org/W6687566353","https://openalex.org/W6697498398","https://openalex.org/W6714031499","https://openalex.org/W6729098122","https://openalex.org/W6736353073"],"related_works":["https://openalex.org/W3163091219","https://openalex.org/W3008130537","https://openalex.org/W2792092810","https://openalex.org/W3201068280","https://openalex.org/W2944787130","https://openalex.org/W2137424107","https://openalex.org/W3169893188","https://openalex.org/W2181990753","https://openalex.org/W3012461129","https://openalex.org/W3014475539","https://openalex.org/W2997887270","https://openalex.org/W2997949149","https://openalex.org/W3160016904","https://openalex.org/W2919685327","https://openalex.org/W2950785196","https://openalex.org/W2620836355","https://openalex.org/W2963785564","https://openalex.org/W3093521632","https://openalex.org/W2888808997","https://openalex.org/W2939224318"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,88,149],"recognition":[2],"is":[3,54,160],"a":[4,28,45],"challenging":[5],"task,":[6],"and":[7,39,58,68,77,103,129,155],"extensive":[8],"reliance":[9],"has":[10],"been":[11],"placed":[12],"on":[13,118],"models":[14,115],"that":[15,35,116],"use":[16],"audio":[17,40,67,119],"features":[18],"in":[19,142],"building":[20],"well-performing":[21],"classifiers.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"propose":[27],"novel":[29],"deep":[30],"dual":[31,72],"recurrent":[32,73],"encoder":[33],"model":[34,62,137,159],"utilizes":[36,106],"text":[37,69],"data":[38,94,111,144],"signals":[41],"simultaneously":[42],"to":[43,85,99,125,145,162,173],"obtain":[44],"better":[46],"understanding":[47],"of":[48,56,131,147],"speech":[49,93],"data.":[50],"As":[51],"emotional":[52],"dialogue":[53],"composed":[55],"sound":[57],"spoken":[59],"content,":[60],"our":[61],"encodes":[63],"the":[64,80,87,96,100,107,110,127,132,158,163],"information":[65,81,108],"from":[66,82,95,171],"sequences":[70],"using":[71],"neural":[74],"networks":[75],"(RNNs)":[76],"then":[78],"combines":[79],"these":[83],"sources":[84],"predict":[86],"class.":[89],"This":[90],"architecture":[91],"analyzes":[92],"signal":[97],"level":[98],"language":[101],"level,":[102],"it":[104],"thus":[105],"within":[109],"more":[112],"comprehensively":[113],"than":[114],"focus":[117],"features.":[120],"Extensive":[121],"experiments":[122],"are":[123],"conducted":[124],"investigate":[126],"efficacy":[128],"properties":[130],"proposed":[133,136],"model.":[134],"Our":[135],"outperforms":[138],"previous":[139],"state-of-the-art":[140],"methods":[141],"assigning":[143],"one":[146],"four":[148],"categories":[150],"(i.e.,":[151],"angry,":[152],"happy,":[153],"sad":[154],"neutral)":[156],"when":[157],"applied":[161],"IEMOCAP":[164],"dataset,":[165],"as":[166],"reflected":[167],"by":[168],"accuracies":[169],"ranging":[170],"68.8%":[172],"71.8%.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}