{"id":"https://openalex.org/W7148616616","doi":"https://doi.org/10.1109/asru65441.2025.11434608","title":"Qieemo: Multimodal Emotion Recognition Based on the ASR Backbone","display_name":"Qieemo: Multimodal Emotion Recognition Based on the ASR Backbone","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148616616","doi":"https://doi.org/10.1109/asru65441.2025.11434608"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5021941627","display_name":"Jinming Chen","orcid":"https://orcid.org/0009-0003-2045-8852"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinming Chen","raw_affiliation_strings":["Qifu Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Qifu Technology,Shanghai,China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009343873","display_name":"Jingyi Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Fang","raw_affiliation_strings":["Qifu Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Qifu Technology,Shanghai,China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108909470","display_name":"Yuanzhong Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhong Zheng","raw_affiliation_strings":["Qifu Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Qifu Technology,Shanghai,China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084443520","display_name":"Yaoxuan Wang","orcid":"https://orcid.org/0000-0003-1002-7242"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoxuan Wang","raw_affiliation_strings":["Qifu Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Qifu Technology,Shanghai,China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025956560","display_name":"Haojun Fei","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojun Fei","raw_affiliation_strings":["Qifu Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Qifu Technology,Shanghai,China","institution_ids":["https://openalex.org/I152269853"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021941627"],"corresponding_institution_ids":["https://openalex.org/I152269853"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81951116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9749000072479248,"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":0.9749000072479248,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0024999999441206455,"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/T10057","display_name":"Face and Expression Recognition","score":0.0015999999595806003,"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/emotion-recognition","display_name":"Emotion recognition","score":0.35850000381469727},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.34940001368522644},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.24619999527931213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5782999992370605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4424999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27649998664855957},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.24619999527931213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2889507358","https://openalex.org/W2963873807","https://openalex.org/W3097777922","https://openalex.org/W3162475537","https://openalex.org/W3163091219","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221162872","https://openalex.org/W4372267501","https://openalex.org/W4390414889","https://openalex.org/W4392904442","https://openalex.org/W4392904469","https://openalex.org/W4395028532","https://openalex.org/W4400454663","https://openalex.org/W4401043060","https://openalex.org/W4402669711","https://openalex.org/W4402743945","https://openalex.org/W4402980768","https://openalex.org/W4406461641"],"related_works":[],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,23,64,119],"plays":[2],"a":[3],"pivotal":[4],"role":[5],"in":[6,48,101],"intelligent":[7],"human-machine":[8],"interaction":[9],"systems.":[10],"Multimodal":[11],"approaches":[12],"benefit":[13],"from":[14],"the":[15,22,26,33,44,54,60,85,91,105,114,125,132],"fusion":[16,93],"of":[17,28,35,142],"diverse":[18],"modalities,":[19],"thereby":[20],"improving":[21,118],"accuracy.":[24,120],"However,":[25],"lack":[27],"high-quality":[29],"multimodal":[30,49,92],"data":[31],"and":[32,74,96,109,136,145],"challenge":[34],"achieving":[36],"optimal":[37],"alignment":[38],"between":[39],"different":[40],"modalities":[41],"significantly":[42],"limit":[43],"potential":[45],"for":[46,117],"improvement":[47],"approaches.":[50],"In":[51],"this":[52],"paper,":[53],"proposed":[55],"Qieemo":[56,130],"framework":[57],"effectively":[58],"utilizes":[59],"pretrained":[61],"automatic":[62],"speech":[63],"(ASR)":[65],"model":[66],"backbone":[67],"which":[68],"contains":[69],"naturally":[70],"frame":[71],"aligned":[72],"textual":[73],"emotional":[75,110],"features,":[76],"to":[77,103],"achieve":[78],"precise":[79],"emotion":[80],"classification":[81],"solely":[82],"based":[83],"on":[84,124],"audio":[86],"modality.":[87],"Furthermore,":[88],"we":[89],"design":[90],"(MMF)":[94],"module":[95,100],"cross-modal":[97],"attention":[98],"(CMA)":[99],"order":[102],"fuse":[104],"phonetic":[106],"posteriorgram":[107],"(PPG)":[108],"features":[111],"extracted":[112],"by":[113],"ASR":[115],"encoder":[116],"The":[121],"experimental":[122],"results":[123],"IEMOCAP":[126],"dataset":[127],"demonstrate":[128],"that":[129],"outperforms":[131],"benchmark":[133],"unimodal,":[134],"multimodal,":[135],"self-supervised":[137],"models":[138],"with":[139],"absolute":[140],"improvements":[141],"3.0%,":[143],"1.2%,":[144],"1.9%":[146],"respectively.":[147]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}