{"id":"https://openalex.org/W4377971642","doi":"https://doi.org/10.1109/lsp.2023.3279689","title":"Speech-Visual Emotion Recognition by Fusing Shared and Specific Features","display_name":"Speech-Visual Emotion Recognition by Fusing Shared and Specific Features","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4377971642","doi":"https://doi.org/10.1109/lsp.2023.3279689"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3279689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3279689","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5100685414","display_name":"Guanghui Chen","orcid":"https://orcid.org/0000-0003-1414-0496"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guanghui Chen","raw_affiliation_strings":["National Mobile Communications Research Laboratory, School of Information Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Laboratory, School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112858962","display_name":"Shuang Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128853","display_name":"China Datang Corporation (China)","ror":"https://ror.org/033mgm122","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Jiao","raw_affiliation_strings":["Central South Electric Power Test Research Institute, China Datang Group Science and Technology Research Institute Company, Ltd., Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"Central South Electric Power Test Research Institute, China Datang Group Science and Technology Research Institute Company, Ltd., Zhengzhou, China","institution_ids":["https://openalex.org/I4210128853"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100685414"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":2.3581,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.88234015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"678","last_page":"682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9988999962806702,"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":0.9988999962806702,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.798404335975647},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7565913796424866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6143840551376343},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5971372127532959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5787255764007568},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.57349693775177},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5624964237213135},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5392258763313293},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.480118989944458},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47981715202331543},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47258126735687256},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47143569588661194},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.42476242780685425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.798404335975647},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7565913796424866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6143840551376343},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5971372127532959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5787255764007568},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.57349693775177},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5624964237213135},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5392258763313293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.480118989944458},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47981715202331543},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47258126735687256},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47143569588661194},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.42476242780685425},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2023.3279689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3279689","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1955055330","https://openalex.org/W2168692779","https://openalex.org/W2336160298","https://openalex.org/W2618530766","https://openalex.org/W2703895418","https://openalex.org/W2889466822","https://openalex.org/W2918087949","https://openalex.org/W2996906606","https://openalex.org/W3049547150","https://openalex.org/W3093051361","https://openalex.org/W3093521632","https://openalex.org/W3121235106","https://openalex.org/W3127521573","https://openalex.org/W3127571973","https://openalex.org/W3128412859","https://openalex.org/W3141819983","https://openalex.org/W3154912261","https://openalex.org/W3155149625","https://openalex.org/W3194672963","https://openalex.org/W3200612871","https://openalex.org/W3209710747","https://openalex.org/W3210588310","https://openalex.org/W3216153120","https://openalex.org/W4213102761","https://openalex.org/W4220887861","https://openalex.org/W4221139382","https://openalex.org/W4280530517","https://openalex.org/W4282598382","https://openalex.org/W4285286860","https://openalex.org/W4293233664","https://openalex.org/W4309568943","https://openalex.org/W4309965782","https://openalex.org/W4312292725","https://openalex.org/W4312402009","https://openalex.org/W4313639160","https://openalex.org/W4315782894","https://openalex.org/W4319300754"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"With":[0],"the":[1,23,35,46,63,73,85,94,103,108,119,126],"development":[2],"of":[3,25,40,48,68,90,113],"artificial":[4],"intelligence,":[5],"it":[6],"has":[7],"become":[8],"a":[9,130],"mainstream":[10],"approach":[11,30],"for":[12],"speech-visual":[13,41,69,91,114],"emotion":[14,49,58],"recognition":[15,59],"by":[16,61],"utilizing":[17],"neural":[18,76],"networks":[19,77,81,89],"to":[20,33,100],"directly":[21],"fuse":[22],"features":[24,39,67,112],"each":[26],"modality.":[27],"However,":[28],"this":[29,52,54],"is":[31,97],"hard":[32],"obtain":[34],"shared":[36,64,109],"and":[37,65,79,93,110],"specific":[38,66,111],"modalities,":[42,92],"which":[43],"seriously":[44],"affects":[45],"performance":[47],"recognition.":[50],"To":[51],"end,":[53],"paper":[55],"proposes":[56],"an":[57],"method":[60,105,128],"fusing":[62],"modalities.":[70,115],"In":[71],"particular,":[72],"three-dimensional":[74],"convolutional":[75],"(3D-CNNs)":[78],"siamese":[80],"are":[82],"applied":[83],"as":[84],"feature":[86],"extraction":[87],"backbone":[88],"loss":[95],"function":[96],"specially":[98],"designed":[99],"ensure":[101],"that":[102,125],"proposed":[104,127],"effectively":[106],"obtains":[107],"Experimental":[116],"results":[117],"on":[118],"RML,":[120],"BAUM-1s,":[121],"eNTERFACE05":[122],"datasets":[123],"show":[124],"achieves":[129],"better":[131],"result.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}