{"id":"https://openalex.org/W4392904444","doi":"https://doi.org/10.1109/icassp48485.2024.10446548","title":"MF-AED-AEC: Speech Emotion Recognition by Leveraging Multimodal Fusion, Asr Error Detection, and Asr Error Correction","display_name":"MF-AED-AEC: Speech Emotion Recognition by Leveraging Multimodal Fusion, Asr Error Detection, and Asr Error Correction","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904444","doi":"https://doi.org/10.1109/icassp48485.2024.10446548"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5101936543","display_name":"Jiajun He","orcid":"https://orcid.org/0009-0006-6489-5220"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiajun He","raw_affiliation_strings":["Nagoya University,Graduate School of Informatics","Graduate School of Informatics, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Graduate School of Informatics","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101796991","display_name":"Xiaohan Shi","orcid":"https://orcid.org/0000-0002-1917-4479"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaohan Shi","raw_affiliation_strings":["Nagoya University,Graduate School of Informatics","Graduate School of Informatics, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Graduate School of Informatics","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101559550","display_name":"Xingfeng Li","orcid":"https://orcid.org/0000-0002-8958-0341"},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingfeng Li","raw_affiliation_strings":["Hainan University,School of Computer Science and Technology","School of Computer Science and Technology, Hainan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hainan University,School of Computer Science and Technology","institution_ids":["https://openalex.org/I20942203"]},{"raw_affiliation_string":"School of Computer Science and Technology, Hainan University","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Information Technology Center","Information Technology Center, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Information Technology Center","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Information Technology Center, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.2124,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.97424322,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11066","last_page":"11070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9991999864578247,"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":0.9991000294685364,"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":0.8367141485214233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7307624220848083},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.582256555557251},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5576229691505432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.511676549911499},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5084766149520874},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.49689772725105286},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48327475786209106},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.450746089220047},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.43360480666160583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3312194347381592},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21476846933364868}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8367141485214233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7307624220848083},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.582256555557251},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5576229691505432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511676549911499},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5084766149520874},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.49689772725105286},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48327475786209106},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.450746089220047},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.43360480666160583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3312194347381592},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21476846933364868},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2358816916","display_name":null,"funder_award_id":"JPMJCR22D1","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G2363020693","display_name":"A Study on Multi-modal Automatic Simultaneous Interpretation System and Evaluation Method","funder_award_id":"21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2146334809","https://openalex.org/W2525778437","https://openalex.org/W2964051877","https://openalex.org/W2973049979","https://openalex.org/W3093051361","https://openalex.org/W3095251683","https://openalex.org/W3096963953","https://openalex.org/W3097969370","https://openalex.org/W3128412859","https://openalex.org/W3160222702","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221162874","https://openalex.org/W4285106979","https://openalex.org/W4285107355","https://openalex.org/W4304098327","https://openalex.org/W4312237773","https://openalex.org/W4323569712","https://openalex.org/W4372260110","https://openalex.org/W4372266796","https://openalex.org/W4385245566","https://openalex.org/W4385571863","https://openalex.org/W4385822510","https://openalex.org/W4387698265","https://openalex.org/W4388717640","https://openalex.org/W4391021742","https://openalex.org/W6631190155","https://openalex.org/W6727690538","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6779068807","https://openalex.org/W6780226713","https://openalex.org/W6794876948","https://openalex.org/W6847363464","https://openalex.org/W6858207737"],"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":{"The":[0],"prevalent":[1],"approach":[2,36,74],"in":[3,69,89,111],"speech":[4,28],"emotion":[5],"recognition":[6,29],"(SER)":[7],"involves":[8],"integrating":[9],"both":[10],"audio":[11],"and":[12,123,136],"textual":[13],"information":[14,88],"to":[15,62,100,128,145,153],"comprehensively":[16],"identify":[17],"the":[18,22,42,47,84,90,93,130,165],"speaker\u2019s":[19],"emotion,":[20],"with":[21],"text":[23,43],"generally":[24],"obtained":[25],"through":[26],"automatic":[27],"(ASR).":[30],"An":[31],"essential":[32],"issue":[33],"of":[34,49,66,86,96,133,171],"this":[35,73,112],"is":[37],"that":[38,161],"ASR":[39,58,70,119,124,134],"errors":[40],"from":[41],"modality":[44],"can":[45],"worsen":[46],"performance":[48],"SER.":[50],"Previous":[51],"studies":[52],"have":[53],"proposed":[54],"using":[55],"an":[56],"auxiliary":[57,117],"error":[59,120,125],"detection":[60,121],"task":[61],"adaptively":[63],"assign":[64],"weights":[65],"each":[67],"word":[68],"hypotheses.":[71],"However,":[72],"has":[75],"limited":[76],"improvement":[77],"potential":[78],"because":[79],"it":[80],"does":[81],"not":[82],"address":[83],"coherence":[85,132],"semantic":[87,131],"text.":[91],"Additionally,":[92],"inherent":[94],"heterogeneity":[95],"different":[97],"modalities":[98],"leads":[99],"distribution":[101],"gaps":[102],"between":[103],"their":[104,107],"representations,":[105],"making":[106],"fusion":[108,142],"challenging.":[109],"Therefore,":[110],"paper,":[113],"we":[114],"incorporate":[115],"two":[116],"tasks,":[118],"(AED)":[122],"correction":[126],"(AEC),":[127],"enhance":[129],"text,":[135],"further":[137],"introduce":[138],"a":[139,169],"novel":[140],"multi-modal":[141],"(MF)":[143],"method":[144,155],"learn":[146],"shared":[147],"representations":[148],"across":[149],"modalities.":[150],"We":[151],"refer":[152],"our":[154],"as":[156],"MF-AED-AEC.":[157],"Experimental":[158],"results":[159],"indicate":[160],"MF-AED-AEC":[162],"significantly":[163],"outperforms":[164],"baseline":[166],"model":[167],"by":[168],"margin":[170],"4.1%.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":8}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}