{"id":"https://openalex.org/W4388821586","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317223","title":"Multilingual, Cross-lingual, and Monolingual Speech Emotion Recognition on EmoFilm Dataset","display_name":"Multilingual, Cross-lingual, and Monolingual Speech Emotion Recognition on EmoFilm Dataset","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821586","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317223"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317223","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5065879041","display_name":"Bagus Tris Atmaja","orcid":"https://orcid.org/0000-0003-1560-2824"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bagus Tris Atmaja","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan","National Institute of Advanced Industrial Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046057045","display_name":"Akira Sasou","orcid":"https://orcid.org/0000-0003-1700-0325"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Sasou","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan","National Institute of Advanced Industrial Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2363,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60939224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"12","issue":null,"first_page":"1019","last_page":"1025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":1.0,"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":1.0,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9925000071525574,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6716375946998596},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6233705878257751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6115636825561523},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5918701887130737},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5384312868118286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3900008797645569},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08868816494941711}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6716375946998596},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6233705878257751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6115636825561523},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5918701887130737},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5384312868118286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3900008797645569},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08868816494941711}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317223","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1608020191","https://openalex.org/W1968001738","https://openalex.org/W2047020576","https://openalex.org/W2107114452","https://openalex.org/W2122348661","https://openalex.org/W2159190230","https://openalex.org/W2514440523","https://openalex.org/W2742542661","https://openalex.org/W2889004077","https://openalex.org/W2902623517","https://openalex.org/W2905903577","https://openalex.org/W2928112693","https://openalex.org/W2939274787","https://openalex.org/W2963087748","https://openalex.org/W2995813704","https://openalex.org/W2997591727","https://openalex.org/W3130621562","https://openalex.org/W3134759918","https://openalex.org/W3197994565","https://openalex.org/W3198771897","https://openalex.org/W3202667537","https://openalex.org/W4296069165","https://openalex.org/W4308521113","https://openalex.org/W4309997606","https://openalex.org/W4312097115","https://openalex.org/W4312951904","https://openalex.org/W4361994820","https://openalex.org/W4362650921","https://openalex.org/W4372267510","https://openalex.org/W6675354045","https://openalex.org/W6809829207","https://openalex.org/W6847020120","https://openalex.org/W6931421704"],"related_works":["https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W2560646951","https://openalex.org/W4297454206","https://openalex.org/W65104662","https://openalex.org/W1871748041","https://openalex.org/W2362286668","https://openalex.org/W3204019825","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Research":[0],"on":[1,47,58,125],"speech":[2,19,43,151],"emotion":[3,16,28,44,65],"recognition":[4,29,45],"has":[5],"been":[6],"actively":[7],"conducted;":[8],"most":[9],"are":[10],"in":[11,18,149],"monolingual":[12,41,100,119,147],"settings.":[13],"Considering":[14],"that":[15,77,117],"expressed":[17],"is":[20,23,121],"universal,":[21],"it":[22],"noteworthy":[24],"to":[25,36,111],"conduct":[26],"multilingual":[27,64,79,142],"across":[30],"different":[31],"cultures.":[32],"This":[33],"paper":[34],"contributes":[35],"evaluating":[37],"multilingual,":[38],"cross-lingual,":[39],"and":[40,97,101,115,146],"automatic":[42],"(SER)":[46],"the":[48,70,78,82,106,118,126,138],"same":[49,127],"EmoFilm":[50],"dataset.":[51],"We":[52,104],"first":[53],"evaluated":[54],"these":[55],"three":[56],"scenarios":[57],"a":[59],"fixed":[60],"training/test":[61],"split.":[62],"For":[63],"recognition,":[66],"we":[67],"then":[68],"expanded":[69],"evaluation":[71],"with":[72,85],"cross-validation.":[73],"The":[74,131],"results":[75,132],"show":[76],"SER":[80,143,148],"gained":[81],"highest":[83],"performance":[84],"74.86%":[86],"of":[87,108,129,133,141],"balanced":[88],"accuracy":[89],"for":[90,99],"five":[91],"categorical":[92],"emotions,":[93],"followed":[94],"by":[95],"72.17%":[96],"58.03%":[98],"cross-lingual":[102,145],"evaluations.":[103],"reduced":[105],"number":[107,128],"training":[109],"samples":[110],"observe":[112],"its":[113],"impact":[114],"found":[116],"setting":[120],"superior":[122],"among":[123],"others":[124],"samples.":[130],"this":[134],"study":[135],"could":[136],"suggest":[137],"potential":[139],"use":[140],"over":[144],"future":[150],"technologies.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}