{"id":"https://openalex.org/W3158929093","doi":"https://doi.org/10.1109/taslp.2021.3076364","title":"Speech Emotion Recognition Considering Nonverbal Vocalization in Affective Conversations","display_name":"Speech Emotion Recognition Considering Nonverbal Vocalization in Affective Conversations","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3158929093","doi":"https://doi.org/10.1109/taslp.2021.3076364","mag":"3158929093"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3076364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3076364","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019460894","display_name":"Jia-Hao Hsu","orcid":"https://orcid.org/0009-0008-5548-2509"},"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":"Jia-Hao Hsu","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":"https://orcid.org/0000-0003-0633-774X","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":"https://orcid.org/0000-0002-3947-2123","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/A5100605918","display_name":"Yi\u2010Hsuan Chen","orcid":"https://orcid.org/0000-0002-4788-5024"},"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":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9227,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.98297072,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"1675","last_page":"1686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9979000091552734,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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/nonverbal-communication","display_name":"Nonverbal communication","score":0.8272259831428528},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7851575613021851},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6007751822471619},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.535261869430542},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5299274325370789},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5233603715896606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4826715290546417},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4444211423397064},{"id":"https://openalex.org/keywords/laughter","display_name":"Laughter","score":0.43410399556159973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37645387649536133},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.2986357510089874},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14449802041053772},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0607873797416687}],"concepts":[{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.8272259831428528},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7851575613021851},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6007751822471619},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.535261869430542},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5299274325370789},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5233603715896606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4826715290546417},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4444211423397064},{"id":"https://openalex.org/C2780775679","wikidata":"https://www.wikidata.org/wiki/Q170579","display_name":"Laughter","level":2,"score":0.43410399556159973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37645387649536133},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2986357510089874},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14449802041053772},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0607873797416687},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3076364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3076364","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4169684317","display_name":null,"funder_award_id":"MOST 108-2221-E-006-103-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1501669607","https://openalex.org/W1825415099","https://openalex.org/W1838628832","https://openalex.org/W1963552095","https://openalex.org/W2037960784","https://openalex.org/W2038821742","https://openalex.org/W2045528981","https://openalex.org/W2053101950","https://openalex.org/W2061688018","https://openalex.org/W2085662862","https://openalex.org/W2094274886","https://openalex.org/W2112796928","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2146334809","https://openalex.org/W2152137767","https://openalex.org/W2153635508","https://openalex.org/W2168465881","https://openalex.org/W2247381151","https://openalex.org/W2317567465","https://openalex.org/W2399733683","https://openalex.org/W2499760652","https://openalex.org/W2510170536","https://openalex.org/W2564768500","https://openalex.org/W2591380794","https://openalex.org/W2626982410","https://openalex.org/W2738561771","https://openalex.org/W2750666523","https://openalex.org/W2785952417","https://openalex.org/W2786779322","https://openalex.org/W2793141922","https://openalex.org/W2803098682","https://openalex.org/W2804161536","https://openalex.org/W2889445231","https://openalex.org/W2889717020","https://openalex.org/W2904581126","https://openalex.org/W2921151609","https://openalex.org/W2938004196","https://openalex.org/W2959546144","https://openalex.org/W2962704885","https://openalex.org/W2962736520","https://openalex.org/W2964308564","https://openalex.org/W2997399314","https://openalex.org/W2997648541","https://openalex.org/W2998563994","https://openalex.org/W3011995592","https://openalex.org/W3023786569","https://openalex.org/W3092104750","https://openalex.org/W3143635792","https://openalex.org/W3155584966","https://openalex.org/W3209383001","https://openalex.org/W4232215321","https://openalex.org/W4246079405","https://openalex.org/W6607193717","https://openalex.org/W6630073874","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6684552223","https://openalex.org/W6776750061","https://openalex.org/W6803793192","https://openalex.org/W7066990553"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2760111529","https://openalex.org/W4304693785","https://openalex.org/W3081604601","https://openalex.org/W2391280397","https://openalex.org/W4238600753","https://openalex.org/W2103493245","https://openalex.org/W4298012685","https://openalex.org/W2063843262","https://openalex.org/W3133700904"],"abstract_inverted_index":{"In":[0,23,41],"real-life":[1,58],"communication,":[2],"nonverbal":[3,32,47,69,152,183],"vocalization":[4,184],"such":[5],"as":[6,134,213,215],"laughter,":[7],"cries":[8],"or":[9],"other":[10],"emotion":[11,21,28,55,91,145,189,207],"interjections,":[12],"within":[13,49],"an":[14,17,50,121,131,201],"utterance":[15,51],"play":[16],"important":[18],"role":[19],"for":[20,54,113,156,176,187,205],"expression.":[22],"previous":[24],"studies,":[25],"only":[26],"few":[27],"recognition":[29,56,135,208],"systems":[30],"consider":[31],"vocalization,":[33],"which":[34,147],"naturally":[35],"exists":[36],"in":[37,166],"our":[38],"daily":[39],"conversation.":[40],"this":[42],"work,":[43],"both":[44],"verbal":[45,67,150],"and":[46,68,92,151,159,218],"sounds":[48],"are":[52,96,118],"considered":[53],"of":[57,108,149,170,203],"affective":[59],"conversations.":[60],"Firstly,":[61],"a":[62,106],"support":[63],"vector":[64],"machine":[65],"(SVM)-based":[66],"sound":[70,85,93],"detector":[71],"is":[72,78],"developed.":[73],"A":[74],"prosodic":[75],"phrase":[76],"auto-tagger":[77],"further":[79],"employed":[80],"to":[81,120,129],"extract":[82],"the":[83,90,100,109,114,167,171,193,210,216],"verbal/nonverbal":[84],"segments.":[86],"For":[87,191],"each":[88],"segment,":[89],"feature":[94,111],"embeddings":[95,112],"respectively":[97],"extracted":[98,110],"using":[99],"deep":[101],"residual":[102],"networks":[103],"(ResNets).":[104],"Finally,":[105],"sequence":[107,133],"entire":[115],"dialog":[116],"turn":[117],"fed":[119],"attentive":[122],"long":[123],"short-term":[124],"memory":[125],"(LSTM)-based":[126],"sequence-to-sequence":[127],"model":[128],"output":[130],"emotional":[132],"result.":[136],"The":[137,178],"NNIME":[138,172],"corpus":[139,173],"(The":[140],"NTHU-NTUA":[141],"Chinese":[142],"interactive":[143],"multimodal":[144],"corpus),":[146],"consists":[148],"sounds,":[153],"was":[154,185],"adopted":[155],"system":[157],"training":[158],"testing.":[160],"4766":[161],"single":[162],"speaker":[163],"dialogue":[164],"turns":[165],"audio":[168],"data":[169],"were":[174],"selected":[175],"evaluation.":[177],"experimental":[179],"results":[180],"showed":[181],"that":[182],"helpful":[186],"speech":[188,206],"recognition.":[190],"comparison,":[192],"proposed":[194],"method":[195],"based":[196],"on":[197],"decision-level":[198],"fusion":[199,220],"achieved":[200],"accuracy":[202],"61.92%":[204],"outperforming":[209],"traditional":[211],"methods":[212],"well":[214],"feature-level":[217],"model-level":[219],"approaches.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":5}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}