{"id":"https://openalex.org/W4224917001","doi":"https://doi.org/10.1109/icassp43922.2022.9746598","title":"Key-Sparse Transformer for Multimodal Speech Emotion Recognition","display_name":"Key-Sparse Transformer for Multimodal Speech Emotion Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224917001","doi":"https://doi.org/10.1109/icassp43922.2022.9746598"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746598","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5104035848","display_name":"Weidong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Chen","raw_affiliation_strings":["South China University of Technology,School of Electronic and Information Engineering,China","School of Electronic and Information Engineering, South China University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Electronic and Information Engineering,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075180992","display_name":"Xiaofeng Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Xing","raw_affiliation_strings":["South China University of Technology,School of Electronic and Information Engineering,China","School of Electronic and Information Engineering, South China University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Electronic and Information Engineering,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007354180","display_name":"Xiangmin Xu","orcid":"https://orcid.org/0000-0003-4573-5820"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangmin Xu","raw_affiliation_strings":["South China University of Technology,School of Electronic and Information Engineering,China","School of Electronic and Information Engineering, South China University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Electronic and Information Engineering,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101406845","display_name":"Jichen Yang","orcid":"https://orcid.org/0000-0003-2655-8304"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jichen Yang","raw_affiliation_strings":["South China University of Technology,School of Electronic and Information Engineering,China","School of Electronic and Information Engineering, South China University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Electronic and Information Engineering,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040709029","display_name":"Jianxin Pang","orcid":"https://orcid.org/0000-0002-3985-5802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianxin Pang","raw_affiliation_strings":["UBTECH Robotics Corp,China","UBTECH Robotics Corp, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UBTECH Robotics Corp,China","institution_ids":[]},{"raw_affiliation_string":"UBTECH Robotics Corp, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6897","last_page":"6901"},"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":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.7766510248184204},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.667229175567627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5666391849517822},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5510361194610596},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4820081293582916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39863619208335876},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32403066754341125},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09985536336898804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766510248184204},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.667229175567627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5666391849517822},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5510361194610596},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4820081293582916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39863619208335876},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32403066754341125},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09985536336898804},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746598","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2060198345","https://openalex.org/W2146334809","https://openalex.org/W2803098682","https://openalex.org/W2896457183","https://openalex.org/W2962770129","https://openalex.org/W2965373594","https://openalex.org/W2972498864","https://openalex.org/W2973049979","https://openalex.org/W2997258743","https://openalex.org/W3016138882","https://openalex.org/W3088631780","https://openalex.org/W3094805191","https://openalex.org/W3095251683","https://openalex.org/W3095379519","https://openalex.org/W3096690837","https://openalex.org/W3096963953","https://openalex.org/W3161003523","https://openalex.org/W3161958798","https://openalex.org/W3214127792","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6776182492","https://openalex.org/W6784497057","https://openalex.org/W6796149595"],"related_works":["https://openalex.org/W2140798747","https://openalex.org/W2948169060","https://openalex.org/W2730112582","https://openalex.org/W2110696645","https://openalex.org/W2358580169","https://openalex.org/W2111347279","https://openalex.org/W4399426197","https://openalex.org/W2487211728","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,69,75],"recognition":[2,70],"is":[3,26,45,65,81],"a":[4,10,40,62],"challenging":[5],"research":[6],"topic":[7],"that":[8,91],"plays":[9],"critical":[11],"role":[12],"in":[13,35],"human-computer":[14],"interaction.":[15],"Multimodal":[16],"inputs":[17],"further":[18],"improve":[19],"the":[20,33,36,56,84,92,99],"performance":[21,97],"as":[22],"more":[23,73],"emotional":[24],"information":[25,34,50],"used.":[27],"However,":[28],"existing":[29],"studies":[30],"learn":[31],"all":[32],"sample":[37],"while":[38],"only":[39],"small":[41],"portion":[42],"of":[43],"it":[44],"about":[46],"emotion.":[47],"The":[48,78],"redundant":[49],"will":[51],"become":[52],"noises":[53],"and":[54,86],"limit":[55],"system":[57],"performance.":[58],"In":[59],"this":[60],"paper,":[61],"key-sparse":[63],"Transformer":[64],"proposed":[66,79,93],"for":[67],"efficient":[68],"by":[71],"focusing":[72],"on":[74,83],"related":[76],"information.":[77],"method":[80,94],"evaluated":[82],"IEMOCAP":[85],"LSSED.":[87],"Experimental":[88],"results":[89],"show":[90],"achieves":[95],"better":[96],"than":[98],"state-of-the-art":[100],"approaches.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}