{"id":"https://openalex.org/W2888792135","doi":"https://doi.org/10.21437/interspeech.2018-1820","title":"A Three-Layer Emotion Perception Model for Valence and Arousal-Based Detection from Multilingual Speech","display_name":"A Three-Layer Emotion Perception Model for Valence and Arousal-Based Detection from Multilingual Speech","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2888792135","doi":"https://doi.org/10.21437/interspeech.2018-1820","mag":"2888792135"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1820","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.jaist.ac.jp/dspace/bitstream/10119/15512/1/InterSpeech2018_Xingfeng.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101559550","display_name":"Xingfeng Li","orcid":"https://orcid.org/0000-0002-8958-0341"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xingfeng Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101559550"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0956,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80144285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3643","last_page":"3647"},"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":0.9909999966621399,"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":0.9904999732971191,"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/valence","display_name":"Valence (chemistry)","score":0.7285857796669006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6992022395133972},{"id":"https://openalex.org/keywords/emotion-detection","display_name":"Emotion detection","score":0.690942645072937},{"id":"https://openalex.org/keywords/arousal","display_name":"Arousal","score":0.6782959699630737},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6493738889694214},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6476650238037109},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5021281242370605},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3958389461040497},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39576709270477295},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.3881481885910034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3407561480998993},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.31177178025245667},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08574768900871277}],"concepts":[{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.7285857796669006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6992022395133972},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.690942645072937},{"id":"https://openalex.org/C36951298","wikidata":"https://www.wikidata.org/wiki/Q379784","display_name":"Arousal","level":2,"score":0.6782959699630737},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6493738889694214},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6476650238037109},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5021281242370605},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3958389461040497},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39576709270477295},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.3881481885910034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3407561480998993},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31177178025245667},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08574768900871277},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1820","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01333:0003026696","is_oa":true,"landing_page_url":"http://hdl.handle.net/10119/15512","pdf_url":"https://dspace.jaist.ac.jp/dspace/bitstream/10119/15512/1/InterSpeech2018_Xingfeng.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc. Interspeech 2018","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01333:0003026696","is_oa":true,"landing_page_url":"http://hdl.handle.net/10119/15512","pdf_url":"https://dspace.jaist.ac.jp/dspace/bitstream/10119/15512/1/InterSpeech2018_Xingfeng.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc. Interspeech 2018","raw_type":"conference paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.6700000166893005,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2888792135.pdf","grobid_xml":"https://content.openalex.org/works/W2888792135.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1964469912","https://openalex.org/W1976725440","https://openalex.org/W2000162405","https://openalex.org/W2003547693","https://openalex.org/W2066090536","https://openalex.org/W2074788634","https://openalex.org/W2079927350","https://openalex.org/W2095176743","https://openalex.org/W2125365056","https://openalex.org/W2149628368","https://openalex.org/W2150556990","https://openalex.org/W2152205330","https://openalex.org/W2154387728","https://openalex.org/W2158630797","https://openalex.org/W2514017951","https://openalex.org/W2568428461"],"related_works":["https://openalex.org/W2029072726","https://openalex.org/W91913183","https://openalex.org/W2936882366","https://openalex.org/W1987182177","https://openalex.org/W2736893848","https://openalex.org/W1544055438","https://openalex.org/W3003450285","https://openalex.org/W2087245461","https://openalex.org/W2085024878","https://openalex.org/W4361008003"],"abstract_inverted_index":{"Automated":[0],"emotion":[1,34,68],"detection":[2,35,69],"from":[3,8,52,107],"speech":[4],"has":[5],"recently":[6],"shifted":[7],"monolingual":[9,33],"to":[10,38,55,62,85,100,117,155],"multilingual":[11],"tasks":[12],"for":[13,149],"human-like":[14],"interaction":[15],"in":[16,40],"real-life":[17],"where":[18],"a":[19,25,60,134],"system":[20,70,126,131],"can":[21],"handle":[22],"more":[23],"than":[24],"single":[26],"input":[27],"language.":[28],"However,":[29],"most":[30],"work":[31,50],"on":[32],"is":[36,82,97],"difficult":[37],"generalize":[39],"multiple":[41,72],"languages,":[42],"because":[43],"the":[44,49,87,128],"optimal":[45],"feature":[46],"sets":[47],"of":[48,78,123],"differ":[51],"one":[53],"language":[54],"another.":[56],"Our":[57],"study":[58],"proposes":[59],"framework":[61],"design,":[63],"implement":[64],"and":[65,80,110,115,139,144],"validate":[66],"an":[67],"using":[71],"corpora.":[73],"A":[74,89],"continuous":[75],"dimensional":[76],"space":[77],"valence":[79],"arousal":[81],"first":[83],"used":[84,99],"describe":[86],"emotions.":[88],"three-layer":[90],"model":[91],"incorporated":[92],"with":[93],"fuzzy":[94],"inference":[95],"systems":[96],"then":[98],"estimate":[101],"two":[102],"dimensions.":[103],"Speech":[104],"features":[105],"derived":[106],"prosodic,":[108],"spectral":[109],"glottal":[111],"waveform":[112],"are":[113,153],"examined":[114],"selected":[116],"capture":[118],"emotional":[119],"cues.":[120],"The":[121],"results":[122,148],"this":[124],"new":[125],"outperformed":[127],"existing":[129],"state-of-the-art":[130],"by":[132],"yielding":[133],"smaller":[135],"mean":[136],"absolute":[137],"error":[138],"higher":[140],"correlation":[141],"between":[142],"estimates":[143],"human":[145,156],"evaluators.":[146,157],"Moreover,":[147],"speaker":[150],"independent":[151],"validation":[152],"comparable":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}