{"id":"https://openalex.org/W3134536060","doi":"https://doi.org/10.1109/icassp39728.2021.9414866","title":"Speech Emotion Recognition Using Semantic Information","display_name":"Speech Emotion Recognition Using Semantic Information","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3134536060","doi":"https://doi.org/10.1109/icassp39728.2021.9414866","mag":"3134536060"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2103.02993","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045277971","display_name":"Panagiotis Tzirakis","orcid":"https://orcid.org/0000-0001-9449-5339"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Panagiotis Tzirakis","raw_affiliation_strings":["GLAM \u2013 Group on Language, Audio, & Music, Imperial College, London, UK","Imperial College London"],"affiliations":[{"raw_affiliation_string":"GLAM \u2013 Group on Language, Audio, & Music, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101706488","display_name":"Anh Gia-Tuan Nguyen","orcid":"https://orcid.org/0000-0003-3606-4199"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anh Nguyen","raw_affiliation_strings":["GLAM \u2013 Group on Language, Audio, & Music, Imperial College, London, UK","GLAM - Group on Language, Audio, & Music, Imperial College London,UK"],"affiliations":[{"raw_affiliation_string":"GLAM \u2013 Group on Language, Audio, & Music, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"GLAM - Group on Language, Audio, & Music, Imperial College London,UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080553022","display_name":"Stefanos Zafeiriou","orcid":"https://orcid.org/0000-0002-5222-1740"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stefanos Zafeiriou","raw_affiliation_strings":["GLAM \u2013 Group on Language, Audio, & Music, Imperial College, London, UK","GLAM - Group on Language, Audio, & Music, Imperial College London,UK"],"affiliations":[{"raw_affiliation_string":"GLAM \u2013 Group on Language, Audio, & Music, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"GLAM - Group on Language, Audio, & Music, Imperial College London,UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]},{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bjorn W. Schuller","raw_affiliation_strings":["GLAM \u2013 Group on Language, Audio, & Music, Imperial College, London, UK","University of Augsburg, Germany","GLAM - Group on Language, Audio, & Music, Imperial College London,UK"],"affiliations":[{"raw_affiliation_string":"GLAM \u2013 Group on Language, Audio, & Music, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"GLAM - Group on Language, Audio, & Music, Imperial College London,UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045277971"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.5506,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67610054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6279","last_page":"6283"},"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":0.9983000159263611,"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":0.998199999332428,"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/paralanguage","display_name":"Paralanguage","score":0.9464136958122253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7619370818138123},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5950226783752441},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.537968099117279},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47808074951171875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45701104402542114},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.44787248969078064},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08092662692070007}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9464136958122253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619370818138123},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5950226783752441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.537968099117279},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47808074951171875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45701104402542114},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.44787248969078064},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08092662692070007},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.02993","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.02993","pdf_url":"https://arxiv.org/pdf/2103.02993","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3134536060","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2103.02993.pdf","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:uni-augsburg.opus-bayern.de:91593","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/91593","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},{"id":"doi:10.48550/arxiv.2103.02993","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.02993","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"},{"id":"doi:10.17023/92hd-8876","is_oa":true,"landing_page_url":"https://doi.org/10.17023/92hd-8876","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2103.02993","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.02993","pdf_url":"https://arxiv.org/pdf/2103.02993","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5192263572","display_name":null,"funder_award_id":"EP/ L016796/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320307901","display_name":"EDS","ror":"https://ror.org/059rn9488"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3134536060.pdf","grobid_xml":"https://content.openalex.org/works/W3134536060.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2080576537","https://openalex.org/W2095705004","https://openalex.org/W2153579005","https://openalex.org/W2339343773","https://openalex.org/W2399733683","https://openalex.org/W2571253853","https://openalex.org/W2610961739","https://openalex.org/W2751214333","https://openalex.org/W2765291577","https://openalex.org/W2766122029","https://openalex.org/W2766925079","https://openalex.org/W2767087747","https://openalex.org/W2786681750","https://openalex.org/W2798536775","https://openalex.org/W2803098682","https://openalex.org/W2804648901","https://openalex.org/W2886300652","https://openalex.org/W2889342907","https://openalex.org/W2892071465","https://openalex.org/W2901531394","https://openalex.org/W2936134684","https://openalex.org/W2962736520","https://openalex.org/W2962770129","https://openalex.org/W2963425185","https://openalex.org/W2972498864","https://openalex.org/W3003908700","https://openalex.org/W3094524767","https://openalex.org/W3094918372","https://openalex.org/W3102444842","https://openalex.org/W4230277160","https://openalex.org/W6631190155","https://openalex.org/W6674330103","https://openalex.org/W6682691769","https://openalex.org/W6751433836"],"related_works":["https://openalex.org/W3163571928","https://openalex.org/W3166353905","https://openalex.org/W2915402499","https://openalex.org/W2967729586","https://openalex.org/W2105251515","https://openalex.org/W2973192491","https://openalex.org/W3094524767","https://openalex.org/W2964018249","https://openalex.org/W2963800675","https://openalex.org/W3160023107","https://openalex.org/W2293363578","https://openalex.org/W2763797558","https://openalex.org/W3010234023","https://openalex.org/W2905137587","https://openalex.org/W3160183718","https://openalex.org/W2019006416","https://openalex.org/W3033625388","https://openalex.org/W2078008248","https://openalex.org/W3175990969","https://openalex.org/W3098610496"],"abstract_inverted_index":{"Speech":[0],"emotion":[1],"recognition":[2],"is":[3,81,124],"a":[4,9,61,84,94,112,116,127],"crucial":[5],"problem":[6],"manifesting":[7],"in":[8,26,43,52,74,134,171],"multitude":[10],"of":[11,34,40,83,145,154],"applications":[12],"such":[13],"as":[14],"human":[15],"computer":[16],"interaction":[17],"and":[18,70,93,105,159,174],"education.":[19],"Although":[20],"several":[21],"advancements":[22],"have":[23],"been":[24],"made":[25],"the":[27,32,41,44,49,53,68,71,75,90,100,131,135,138,143,150,155,162,172],"recent":[28],"years,":[29],"especially":[30],"with":[31,161],"advent":[33],"Deep":[35],"Neural":[36],"Networks":[37],"(DNN),":[38],"most":[39],"studies":[42],"literature":[45],"fail":[46],"to":[47,111,129],"consider":[48],"semantic":[50,69,85,91,104],"information":[51,73],"speech":[54],"signal.":[55,76],"In":[56,77],"this":[57],"paper,":[58],"we":[59,148],"propose":[60],"novel":[62,117],"framework":[63,80],"that":[64,88,98],"can":[65],"capture":[66,130],"both":[67],"paralinguistic":[72,95,101],"particular,":[78],"our":[79,146],"comprised":[82],"feature":[86,96,122],"extractor,":[87,97],"captures":[89,99],"information,":[92],"information.":[102],"Both":[103],"paraliguistic":[106],"features":[107],"are":[108],"then":[109],"combined":[110],"unified":[113,121],"representation":[114],"using":[115],"attention":[118],"mechanism.":[119],"The":[120],"vector":[123],"passed":[125],"through":[126],"LSTM":[128],"temporal":[132],"dynamics":[133],"signal,":[136],"before":[137],"final":[139],"prediction.":[140],"To":[141],"validate":[142],"effectiveness":[144],"framework,":[147],"use":[149],"popular":[151],"SEWA":[152],"dataset":[153],"AVEC":[156],"challenge":[157],"series":[158],"compare":[160],"three":[163],"winning":[164],"papers.":[165],"Our":[166],"model":[167],"provides":[168],"state-of-the-art":[169],"results":[170],"valence":[173],"liking":[175],"dimensions.":[176],"<sup":[177],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[178],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[179]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}