{"id":"https://openalex.org/W4387587653","doi":"https://doi.org/10.1109/lsp.2023.3324294","title":"Speech-Visual Emotion Recognition via Modal Decomposition Learning","display_name":"Speech-Visual Emotion Recognition via Modal Decomposition Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387587653","doi":"https://doi.org/10.1109/lsp.2023.3324294"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3324294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3324294","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/A5100727433","display_name":"Lei Bai","orcid":"https://orcid.org/0009-0002-4409-3125"},"institutions":[{"id":"https://openalex.org/I198645480","display_name":"North China University of Water Resources and Electric Power","ror":"https://ror.org/03acrzv41","country_code":"CN","type":"education","lineage":["https://openalex.org/I198645480"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Bai","raw_affiliation_strings":["School of Electrical Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China","institution_ids":["https://openalex.org/I198645480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102825285","display_name":"Rui Chang","orcid":"https://orcid.org/0000-0003-0629-2596"},"institutions":[{"id":"https://openalex.org/I198645480","display_name":"North China University of Water Resources and Electric Power","ror":"https://ror.org/03acrzv41","country_code":"CN","type":"education","lineage":["https://openalex.org/I198645480"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Chang","raw_affiliation_strings":["School of Electrical Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China","institution_ids":["https://openalex.org/I198645480"]}]},{"author_position":"middle","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":false,"raw_author_name":"Guanghui Chen","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101587227","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0001-9572-0710"},"institutions":[{"id":"https://openalex.org/I198645480","display_name":"North China University of Water Resources and Electric Power","ror":"https://ror.org/03acrzv41","country_code":"CN","type":"education","lineage":["https://openalex.org/I198645480"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["School of Electrical Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China","institution_ids":["https://openalex.org/I198645480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100727433"],"corresponding_institution_ids":["https://openalex.org/I198645480"],"apc_list":null,"apc_paid":null,"fwci":0.8133,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72385304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"1452","last_page":"1456"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9983000159263611,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9729999899864197,"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":0.8054518699645996},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6314111948013306},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6288306713104248},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6237777471542358},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5723075270652771},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5073320269584656},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47619807720184326},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47269630432128906},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44705596566200256},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43185630440711975},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07361572980880737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8054518699645996},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6314111948013306},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6288306713104248},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6237777471542358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5723075270652771},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5073320269584656},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47619807720184326},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47269630432128906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44705596566200256},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43185630440711975},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07361572980880737},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2023.3324294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3324294","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":[{"id":"https://metadata.un.org/sdg/16","score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G6997970493","display_name":null,"funder_award_id":"U1504622","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2336160298","https://openalex.org/W2703895418","https://openalex.org/W2803193013","https://openalex.org/W2889466822","https://openalex.org/W2918087949","https://openalex.org/W2996906606","https://openalex.org/W3005680577","https://openalex.org/W3042183479","https://openalex.org/W3094378471","https://openalex.org/W3094502228","https://openalex.org/W3127521573","https://openalex.org/W3186351311","https://openalex.org/W3203381531","https://openalex.org/W3209494353","https://openalex.org/W4213102761","https://openalex.org/W4220766673","https://openalex.org/W4220829848","https://openalex.org/W4280581388","https://openalex.org/W4282598382","https://openalex.org/W4285244280","https://openalex.org/W4285281531","https://openalex.org/W4289946024","https://openalex.org/W4292794012","https://openalex.org/W4309568943","https://openalex.org/W4312402009","https://openalex.org/W4313178214","https://openalex.org/W4319430578","https://openalex.org/W4319430585","https://openalex.org/W4362721809","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6774314701","https://openalex.org/W6784333009","https://openalex.org/W6803136910","https://openalex.org/W6837937255","https://openalex.org/W7028336066"],"related_works":["https://openalex.org/W2354322770","https://openalex.org/W3000097931","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1924837940","https://openalex.org/W2379407973","https://openalex.org/W4243305035","https://openalex.org/W2079488604","https://openalex.org/W2125195795"],"abstract_inverted_index":{"It":[0,72],"is":[1],"becoming":[2],"a":[3,37,63,82,138],"mainstream":[4],"feature":[5],"fusion":[6],"approach":[7],"for":[8],"speech-visual":[9],"emotion":[10],"recognition":[11],"(SVER)":[12],"by":[13],"directly":[14],"using":[15],"neural":[16],"networks":[17],"to":[18,86,100],"fuse":[19],"the":[20,27,44,52,55,68,74,88,95,102,110,117,125,134],"extracted":[21,45,89,118],"speech":[22,30,46,90,119],"and":[23,31,40,47,77,91,97,104,113,120,128],"visual":[24,32,48,92,121],"features.":[25,122],"However,":[26],"heterogeneity":[28],"between":[29,43,116],"modalities":[33],"usually":[34],"results":[35],"in":[36],"distribution":[38,111],"gap":[39,112],"information":[41,114],"redundancy":[42,115],"features,":[49,106],"thus":[50],"affecting":[51],"performance":[53],"of":[54],"SVER.":[56],"To":[57],"this":[58,60],"end,":[59],"paper":[61],"proposes":[62],"SVER":[64],"method":[65,136],"based":[66],"on":[67,124],"modal":[69,79],"decomposition":[70],"learning.":[71],"leverages":[73],"shared,":[75],"private":[76,98,105],"reconstructed":[78],"learning":[80],"with":[81],"specifically":[83],"designed":[84],"loss":[85],"decompose":[87],"features":[93],"into":[94],"shared":[96,103],"subspaces":[99],"obtain":[101],"which":[107],"effectively":[108],"reduces":[109],"Experiments":[123],"BAUM-1s,":[126],"RAVDESS":[127],"eNTERFACE05":[129],"datasets":[130],"also":[131],"show":[132],"that":[133],"proposed":[135],"achieves":[137],"better":[139],"result.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}