{"id":"https://openalex.org/W4372267501","doi":"https://doi.org/10.1109/icassp49357.2023.10096709","title":"Exploring Complementary Features in Multi-Modal Speech Emotion Recognition","display_name":"Exploring Complementary Features in Multi-Modal Speech Emotion Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267501","doi":"https://doi.org/10.1109/icassp49357.2023.10096709"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5101908213","display_name":"Suzhen Wang","orcid":"https://orcid.org/0000-0001-7271-4481"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Suzhen Wang","raw_affiliation_strings":["Virtual Human Group,Netease Fuxi AI Lab,China","Netease Fuxi AI Lab, Virtual Human Group, China"],"affiliations":[{"raw_affiliation_string":"Virtual Human Group,Netease Fuxi AI Lab,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"Netease Fuxi AI Lab, Virtual Human Group, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043012868","display_name":"Yifeng Ma","orcid":"https://orcid.org/0000-0001-5243-9806"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifeng Ma","raw_affiliation_strings":["Tsinghua University,China","Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101853531","display_name":"Yu Ding","orcid":"https://orcid.org/0000-0003-1834-4429"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Ding","raw_affiliation_strings":["Virtual Human Group,Netease Fuxi AI Lab,China","Netease Fuxi AI Lab, Virtual Human Group, China"],"affiliations":[{"raw_affiliation_string":"Virtual Human Group,Netease Fuxi AI Lab,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"Netease Fuxi AI Lab, Virtual Human Group, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101908213"],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":4.9752,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.9550772,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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/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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9929999709129333,"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":0.7911854386329651},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7004916071891785},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5686754584312439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49539148807525635},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4564521312713623},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3369947075843811},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32874828577041626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7911854386329651},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7004916071891785},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5686754584312439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49539148807525635},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4564521312713623},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3369947075843811},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32874828577041626},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2032254851","https://openalex.org/W2146334809","https://openalex.org/W2550557083","https://openalex.org/W2896457183","https://openalex.org/W2962770129","https://openalex.org/W2964266095","https://openalex.org/W3016473712","https://openalex.org/W3036601975","https://openalex.org/W3088631780","https://openalex.org/W3094805191","https://openalex.org/W3095251683","https://openalex.org/W3096963953","https://openalex.org/W3160039712","https://openalex.org/W3161958798","https://openalex.org/W3197977579","https://openalex.org/W3198528147","https://openalex.org/W3209059054","https://openalex.org/W4224916926","https://openalex.org/W4224917001","https://openalex.org/W4385245566","https://openalex.org/W6755207826","https://openalex.org/W6776148200","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,73,85,132],"recognition":[2,74],"(SER)":[3],"is":[4,44],"of":[5,35,58,116,122,130,175,215],"great":[6],"importance":[7],"in":[8,24,39,54,87,151,160,179],"human-computer":[9],"interaction.":[10],"Recent":[11],"research":[12],"has":[13],"demonstrated":[14],"that":[15],"self-supervised":[16],"learned":[17],"acoustic":[18,143],"and":[19,90,144,182,196,199,206],"linguistic":[20,145],"features":[21,38,57,86,115,146],"are":[22],"helpful":[23],"this":[25,64,184],"task.":[26],"However,":[27],"few":[28],"works":[29],"have":[30],"fully":[31],"exploit":[32,82],"the":[33,36,49,55,59,83,93,103,109,113,123,137,141,148,152,156,165,173,176,191,203,213,216],"advantages":[34],"pre-trained":[37,56,114],"SER.":[40],"The":[41],"primary":[42],"challenge":[43],"how":[45],"to":[46,81,107,135,171],"effectively":[47],"extract":[48],"complementary":[50,94],"emotional":[51,95,138,177],"information":[52,96,111,139,178],"implied":[53],"respective":[60],"modality.":[61,118],"To":[62],"tackle":[63],"challenge,":[65],"we":[66,79,100,126,163],"propose":[67],"a":[68,77,128],"novel":[69],"modality-sensitive":[70],"multimodal":[71,124,161],"speech":[72],"framework.":[75],"In":[76],"nutshell,":[78],"aim":[80],"typical":[84],"each":[88,117,180],"modality":[89,157,167,181],"then":[91],"fuse":[92],"for":[97],"classification.":[98],"Specifically,":[99],"first":[101],"utilize":[102],"parallel":[104],"uni-modal":[105],"encoders":[106],"refine":[108],"emotion-related":[110],"from":[112,140],"For":[119],"better":[120],"fusion":[121],"features,":[125],"develop":[127],"group":[129],"learnable":[131],"query":[133],"tokens":[134],"gather":[136],"refined":[142],"with":[147],"cross-attention":[149],"mechanism":[150],"transformer":[153],"decoder.":[154],"Observing":[155],"bias":[158],"problem":[159],"methods,":[162],"introduce":[164],"random":[166],"masking":[168],"training":[169],"strategy":[170],"maximize":[172],"utilization":[174],"mitigate":[183],"problem.":[185],"We":[186],"evaluate":[187],"our":[188],"method":[189],"on":[190,202],"widely":[192],"used":[193],"IEMOCAP":[194],"dataset":[195],"achieve":[197],"1.1%":[198],"0.9%":[200],"improvements":[201],"unweighted":[204],"accuracy":[205],"weighted":[207],"accuracy,":[208],"respectively.":[209],"Extensive":[210],"experiments":[211],"demonstrate":[212],"effectiveness":[214],"proposed":[217],"method.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-24T08:23:43.765630","created_date":"2025-10-10T00:00:00"}