{"id":"https://openalex.org/W2938004196","doi":"https://doi.org/10.1109/icassp.2019.8682283","title":"Speech Emotion Recognition Using Deep Neural Network Considering Verbal and Nonverbal Speech Sounds","display_name":"Speech Emotion Recognition Using Deep Neural Network Considering Verbal and Nonverbal Speech Sounds","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938004196","doi":"https://doi.org/10.1109/icassp.2019.8682283","mag":"2938004196"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5065699174","display_name":"Kun-Yi Huang","orcid":"https://orcid.org/0000-0002-3629-7091"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kun-Yi Huang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103251327","display_name":"Chung\u2010Hsien Wu","orcid":"https://orcid.org/0000-0002-3947-2123"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Hsien Wu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054849851","display_name":"Qian-Bei Hong","orcid":"https://orcid.org/0000-0003-2123-1601"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Qian-Bei Hong","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091093449","display_name":"Ming-Hsiang Su","orcid":"https://orcid.org/0000-0003-0633-774X"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Hsiang Su","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100605916","display_name":"Yi\u2010Hsuan Chen","orcid":"https://orcid.org/0000-0002-2796-4198"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Chen","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.5949,"has_fulltext":false,"cited_by_count":118,"citation_normalized_percentile":{"value":0.99264519,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5866","last_page":"5870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9887999892234802,"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/T13289","display_name":"Infant Health and Development","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7872436046600342},{"id":"https://openalex.org/keywords/nonverbal-communication","display_name":"Nonverbal communication","score":0.7603332996368408},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6867548227310181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6553058624267578},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5187985301017761},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5044790506362915},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.48919299244880676},{"id":"https://openalex.org/keywords/laughter","display_name":"Laughter","score":0.48415499925613403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46301835775375366},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.4593307375907898},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43729448318481445},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4299640953540802},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23196032643318176},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.18836930394172668},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08059647679328918}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7872436046600342},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.7603332996368408},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6867548227310181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6553058624267578},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5187985301017761},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5044790506362915},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48919299244880676},{"id":"https://openalex.org/C2780775679","wikidata":"https://www.wikidata.org/wiki/Q170579","display_name":"Laughter","level":2,"score":0.48415499925613403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46301835775375366},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.4593307375907898},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43729448318481445},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4299640953540802},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23196032643318176},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.18836930394172668},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08059647679328918},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1838628832","https://openalex.org/W1963552095","https://openalex.org/W1992810401","https://openalex.org/W2037960784","https://openalex.org/W2038821742","https://openalex.org/W2085662862","https://openalex.org/W2152137767","https://openalex.org/W2168465881","https://openalex.org/W2247381151","https://openalex.org/W2317567465","https://openalex.org/W2399733683","https://openalex.org/W2499760652","https://openalex.org/W2564768500","https://openalex.org/W2591380794","https://openalex.org/W2738561771","https://openalex.org/W2785952417","https://openalex.org/W2786779322","https://openalex.org/W2793141922","https://openalex.org/W2803098682","https://openalex.org/W2904581126"],"related_works":["https://openalex.org/W2760111529","https://openalex.org/W4304693785","https://openalex.org/W3081604601","https://openalex.org/W4238600753","https://openalex.org/W2103493245","https://openalex.org/W4298012685","https://openalex.org/W2391280397","https://openalex.org/W2063843262","https://openalex.org/W2174919855","https://openalex.org/W4385559915"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,33,45,69,99,170],"recognition":[2,34,70,151,157],"is":[3],"becoming":[4],"increasingly":[5],"important":[6,21],"for":[7,23,68,129],"many":[8],"applications.":[9],"In":[10,28,54],"real-life":[11,72],"communication,":[12],"non-verbal":[13],"sounds":[14,61],"within":[15,62],"an":[16,20,63,75,130,137,147],"utterance":[17,64],"also":[18],"play":[19],"role":[22],"people":[24],"to":[25,90,115,136,145],"recognize":[26],"emotion.":[27],"current":[29],"studies,":[30],"only":[31],"few":[32],"systems":[35],"considered":[36,67],"nonverbal":[37,60],"sounds,":[38],"such":[39],"as":[40,150],"laughter,":[41],"cries":[42],"or":[43],"other":[44],"interjection,":[46],"which":[47],"naturally":[48],"exists":[49],"in":[50,162],"our":[51],"daily":[52],"conversation.":[53],"this":[55],"work,":[56],"both":[57],"verbal":[58],"and":[59,100,112],"were":[65,103],"thus":[66],"of":[71,125,158,181],"conversations.":[73],"Firstly,":[74],"SVM-based":[76],"verbal/nonverbal":[77,93],"sound":[78,101],"detector":[79],"was":[80,87,134],"developed.":[81],"A":[82],"Prosodic":[83],"Phrase":[84],"(PPh)":[85],"auto-tagger":[86],"further":[88],"employed":[89],"extract":[91],"the":[92,98,156,163,174,184],"segments.":[94],"For":[95],"each":[96],"segment,":[97],"features":[102],"respectively":[104],"extracted":[105],"based":[106],"on":[107,155],"convolutional":[108],"neural":[109],"networks":[110],"(CNNs)":[111],"then":[113],"concatenated":[114],"form":[116],"a":[117,123,178],"CNN-based":[118,126],"generic":[119],"feature":[120,127],"vector.":[121],"Finally,":[122],"sequence":[124,149],"vectors":[128],"entire":[131],"dialog":[132],"turn":[133],"fed":[135],"attentive":[138],"long":[139],"short-term":[140],"memory":[141],"(LSTM)-based":[142],"sequence-to-sequence":[143],"model":[144],"output":[146],"emotional":[148,160],"result.":[152],"Experimental":[153],"results":[154],"seven":[159],"states":[161],"NNIME":[164],"(The":[165],"NTHU-NTUA":[166],"Chinese":[167],"interactive":[168],"multimodal":[169],"corpus)":[171],"showed":[172],"that":[173],"proposed":[175],"method":[176],"achieved":[177],"detection":[179],"accuracy":[180],"52.00%":[182],"outperforming":[183],"traditional":[185],"methods.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}