{"id":"https://openalex.org/W3088789516","doi":"https://doi.org/10.3390/s20195559","title":"Fusing Visual Attention CNN and Bag of Visual Words for Cross-Corpus Speech Emotion Recognition","display_name":"Fusing Visual Attention CNN and Bag of Visual Words for Cross-Corpus Speech Emotion Recognition","publication_year":2020,"publication_date":"2020-09-28","ids":{"openalex":"https://openalex.org/W3088789516","doi":"https://doi.org/10.3390/s20195559","mag":"3088789516","pmid":"https://pubmed.ncbi.nlm.nih.gov/32998382"},"language":"en","primary_location":{"id":"doi:10.3390/s20195559","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s20195559","pdf_url":"https://www.mdpi.com/1424-8220/20/19/5559/pdf?version=1601296315","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/20/19/5559/pdf?version=1601296315","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101953815","display_name":"Minji Seo","orcid":"https://orcid.org/0000-0002-7564-9264"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minji Seo","raw_affiliation_strings":["Department of Software Convergence, Soongsil University, 369, Sangdo-ro, Dongjak-gu, Seoul 06978, Korea"],"raw_orcid":"https://orcid.org/0000-0002-7564-9264","affiliations":[{"raw_affiliation_string":"Department of Software Convergence, Soongsil University, 369, Sangdo-ro, Dongjak-gu, Seoul 06978, Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089431420","display_name":"Myung Ho Kim","orcid":"https://orcid.org/0000-0002-1933-7987"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Myungho Kim","raw_affiliation_strings":["Department of Software Convergence, Soongsil University, 369, Sangdo-ro, Dongjak-gu, Seoul 06978, Korea"],"raw_orcid":"https://orcid.org/0000-0002-1933-7987","affiliations":[{"raw_affiliation_string":"Department of Software Convergence, Soongsil University, 369, Sangdo-ro, Dongjak-gu, Seoul 06978, Korea","institution_ids":["https://openalex.org/I141371507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089431420"],"corresponding_institution_ids":["https://openalex.org/I141371507"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":4.142,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94558908,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"20","issue":"19","first_page":"5559","last_page":"5559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9993000030517578,"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":0.9993000030517578,"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/T13731","display_name":"Advanced Computing and Algorithms","score":0.9857000112533569,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/computer-science","display_name":"Computer science","score":0.72920161485672},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7138811945915222},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6941066980361938},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6862384080886841},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6601749658584595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5992529392242432},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5516732931137085},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43842121958732605},{"id":"https://openalex.org/keywords/bag-of-words-model-in-computer-vision","display_name":"Bag-of-words model in computer vision","score":0.42299288511276245},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.41920650005340576},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41647329926490784},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.4102199673652649},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40741217136383057},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.3350730836391449},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27877575159072876},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.14012396335601807},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07693547010421753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72920161485672},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7138811945915222},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6941066980361938},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6862384080886841},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6601749658584595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5992529392242432},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5516732931137085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43842121958732605},{"id":"https://openalex.org/C167611913","wikidata":"https://www.wikidata.org/wiki/Q6884747","display_name":"Bag-of-words model in computer vision","level":5,"score":0.42299288511276245},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.41920650005340576},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41647329926490784},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.4102199673652649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40741217136383057},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.3350730836391449},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27877575159072876},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.14012396335601807},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07693547010421753},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010465","descriptor_name":"Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010465","descriptor_name":"Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010465","descriptor_name":"Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010465","descriptor_name":"Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s20195559","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s20195559","pdf_url":"https://www.mdpi.com/1424-8220/20/19/5559/pdf?version=1601296315","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:32998382","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32998382","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:dd108fd2421c42de81126b5a88684ed4","is_oa":true,"landing_page_url":"https://doaj.org/article/dd108fd2421c42de81126b5a88684ed4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 20, Iss 19, p 5559 (2020)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/20/19/5559/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s20195559","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 20; Issue 19; Pages: 5559","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:7583996","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7583996","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s20195559","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s20195559","pdf_url":"https://www.mdpi.com/1424-8220/20/19/5559/pdf?version=1601296315","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G7806747023","display_name":null,"funder_award_id":"IITP-2020-2018-0-01419","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3088789516.pdf","grobid_xml":"https://content.openalex.org/works/W3088789516.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W589698015","https://openalex.org/W1799366690","https://openalex.org/W1902237438","https://openalex.org/W1971673631","https://openalex.org/W2018549299","https://openalex.org/W2077061001","https://openalex.org/W2087618018","https://openalex.org/W2123045220","https://openalex.org/W2125462608","https://openalex.org/W2146334809","https://openalex.org/W2157297238","https://openalex.org/W2168045655","https://openalex.org/W2168692779","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2322208196","https://openalex.org/W2336160298","https://openalex.org/W2416278874","https://openalex.org/W2500376910","https://openalex.org/W2512885694","https://openalex.org/W2550553598","https://openalex.org/W2561238782","https://openalex.org/W2624340939","https://openalex.org/W2625297138","https://openalex.org/W2738561771","https://openalex.org/W2752782242","https://openalex.org/W2766219234","https://openalex.org/W2766272105","https://openalex.org/W2795783309","https://openalex.org/W2803193013","https://openalex.org/W2811374032","https://openalex.org/W2858643988","https://openalex.org/W2884585870","https://openalex.org/W2885005742","https://openalex.org/W2887280559","https://openalex.org/W2888796689","https://openalex.org/W2903369016","https://openalex.org/W2904938641","https://openalex.org/W2944458161","https://openalex.org/W2944782230","https://openalex.org/W2951559372","https://openalex.org/W2959229524","https://openalex.org/W2959546144","https://openalex.org/W2963322224","https://openalex.org/W2963420686","https://openalex.org/W2963929227","https://openalex.org/W2972498864","https://openalex.org/W2972691009","https://openalex.org/W2972691905","https://openalex.org/W2980587061","https://openalex.org/W2989798836","https://openalex.org/W2990079977","https://openalex.org/W2991147398","https://openalex.org/W2995813704","https://openalex.org/W2997399314","https://openalex.org/W2997700007","https://openalex.org/W3004319605","https://openalex.org/W3008554267","https://openalex.org/W3012473796","https://openalex.org/W3027701939","https://openalex.org/W3040396712","https://openalex.org/W3044927199","https://openalex.org/W3083424454","https://openalex.org/W3141819983","https://openalex.org/W4250482878","https://openalex.org/W6687483927","https://openalex.org/W6786585944"],"related_works":["https://openalex.org/W2158102958","https://openalex.org/W2028757524","https://openalex.org/W2938717424","https://openalex.org/W1995462736","https://openalex.org/W2548286644","https://openalex.org/W2009049007","https://openalex.org/W2588241640","https://openalex.org/W2045213079","https://openalex.org/W2465112410","https://openalex.org/W2616303661"],"abstract_inverted_index":{"Speech":[0,161,170],"emotion":[1,35],"recognition":[2],"(SER)":[3],"classifies":[4],"emotions":[5],"using":[6,22,36,66,99],"low-level":[7],"features":[8,116,129],"or":[9],"a":[10,77,100,136],"spectrogram":[11,133],"of":[12,62,102,139,149,159,168,187],"an":[13,146],"utterance.":[14],"When":[15],"SER":[16,31,43,55,197],"methods":[17],"are":[18],"trained":[19],"and":[20,39,84,127,152,162,172,190],"tested":[21],"different":[23,37],"datasets,":[24],"they":[25],"have":[26],"shown":[27],"performance":[28],"reduction.":[29],"Cross-corpus":[30],"research":[32,44],"identifies":[33],"speech":[34],"corpora":[38],"languages.":[40],"Recent":[41],"cross-corpus":[42,54,196],"has":[45,76],"been":[46],"conducted":[47],"to":[48,106,124,193],"improve":[49,52],"generalization.":[50],"To":[51,89],"the":[53,59,63,91,96,108,118,120,131,155,165],"performance,":[56],"we":[57,94],"pretrained":[58],"log-mel":[60,132],"spectrograms":[61],"source":[64],"dataset":[65],"our":[67],"designed":[68],"visual":[69,86,103,112,140],"attention":[70,87],"convolutional":[71],"neural":[72],"network":[73],"(VACNN),":[74],"which":[75],"2D":[78],"CNN":[79],"base":[80],"model":[81],"with":[82],"channel-":[83],"spatial-wise":[85],"modules.":[88],"train":[90],"target":[92],"dataset,":[93],"extracted":[95],"feature":[97],"vector":[98],"bag":[101],"words":[104,113],"(BOVW)":[105],"assist":[107],"fine-tuned":[109],"model.":[110],"Because":[111],"represent":[114],"local":[115,128],"in":[117,130,154],"image,":[119],"BOVW":[121],"helps":[122],"VACNN":[123],"learn":[125],"global":[126],"by":[134],"constructing":[135],"frequency":[137],"histogram":[138],"words.":[141],"The":[142],"proposed":[143],"method":[144],"shows":[145],"overall":[147],"accuracy":[148],"83.33%,":[150],"86.92%,":[151],"75.00%":[153],"Ryerson":[156],"Audio-Visual":[157,174],"Database":[158,167],"Emotional":[160,169],"Song":[163],"(RAVDESS),":[164],"Berlin":[166],"(EmoDB),":[171],"Surrey":[173],"Expressed":[175],"Emotion":[176],"(SAVEE),":[177],"respectively.":[178],"Experimental":[179],"results":[180],"on":[181],"RAVDESS,":[182],"EmoDB,":[183],"SAVEE":[184],"demonstrate":[185],"improvements":[186],"7.73%,":[188],"15.12%,":[189],"2.34%":[191],"compared":[192],"existing":[194],"state-of-the-art":[195],"approaches.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}