{"id":"https://openalex.org/W7148379406","doi":"https://doi.org/10.1109/asru65441.2025.11434758","title":"Intermediate-Selective Feature Enhancement for Speech Emotion Recognition","display_name":"Intermediate-Selective Feature Enhancement for Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148379406","doi":"https://doi.org/10.1109/asru65441.2025.11434758"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434758","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/A5056529155","display_name":"Y. Li","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":true,"raw_author_name":"Yangbiao Li","raw_affiliation_strings":["South China University of Technology,School of Future Technology,China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Future Technology,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132796937","display_name":"Xiaofen 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":"Xiaofen Xing","raw_affiliation_strings":["South China University of Technology,School of Electronic and Information Engineering,China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Electronic and Information Engineering,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310846","display_name":"Jialong Mai","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":"Jialong Mai","raw_affiliation_strings":["South China University of Technology,School of Electronic and Information Engineering,China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Electronic and Information Engineering,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132816534","display_name":"Jingyuan 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":"Jingyuan Xing","raw_affiliation_strings":["South China University of Technology,School of Future Technology,China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Future Technology,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132812213","display_name":"Xiangmin Xu","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":"Xiangmin Xu","raw_affiliation_strings":["South China University of Technology,School of Future Technology,China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Future Technology,China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056529155"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81908506,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8689000010490417,"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":0.8689000010490417,"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/T10057","display_name":"Face and Expression Recognition","score":0.020600000396370888,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.014999999664723873,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5370000004768372},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4284000098705292},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.29319998621940613},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2872999906539917},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2773999869823456}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5582000017166138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5554999709129333},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5370000004768372},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40549999475479126},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3086000084877014},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434758","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":30,"referenced_works":["https://openalex.org/W2033688243","https://openalex.org/W2146334809","https://openalex.org/W2940259008","https://openalex.org/W2943994882","https://openalex.org/W2963686995","https://openalex.org/W2997399314","https://openalex.org/W3160799772","https://openalex.org/W3209984917","https://openalex.org/W4224917001","https://openalex.org/W4226380987","https://openalex.org/W4319862479","https://openalex.org/W4372259942","https://openalex.org/W4372266552","https://openalex.org/W4372266717","https://openalex.org/W4375869114","https://openalex.org/W4385807453","https://openalex.org/W4385823394","https://openalex.org/W4392172995","https://openalex.org/W4392903514","https://openalex.org/W4392904442","https://openalex.org/W4402111701","https://openalex.org/W4402112182","https://openalex.org/W4402112330","https://openalex.org/W4402112382","https://openalex.org/W4402112384","https://openalex.org/W4402112465","https://openalex.org/W4405179268","https://openalex.org/W4408353379","https://openalex.org/W4408354325","https://openalex.org/W4408355828"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"plays":[4],"a":[5,40,67],"vital":[6],"role":[7],"in":[8,21,30,100],"enabling":[9],"intelligent":[10],"systems":[11],"to":[12,16,27,71],"perceive":[13],"and":[14,88,108],"respond":[15],"human":[17],"emotions.":[18],"Recent":[19],"advances":[20],"large":[22],"pretrained":[23,77],"models":[24],"have":[25],"led":[26],"substantial":[28],"improvements":[29],"SER":[31],"performance.":[32],"However,":[33],"most":[34],"existing":[35],"approaches":[36],"focus":[37],"solely":[38],"on":[39,105],"single":[41],"layer":[42,95],"representation":[43],"or":[44],"perform":[45],"layer-wise":[46],"fusion,":[47],"which":[48],"may":[49],"not":[50],"be":[51],"optimal":[52],"for":[53,128],"downstream":[54],"emotion":[55],"recognition":[56],"tasks.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61],"propose":[62],"ISFE":[63,86,113],"(Intermediate-Selective":[64],"Feature":[65],"Enhancement),":[66],"novel":[68],"framework":[69],"designed":[70],"enhance":[72],"the":[73,106,122],"emotional":[74],"expressiveness":[75],"of":[76,124],"representations.":[78],"Rather":[79],"than":[80,117],"fusing":[81],"features":[82,127],"across":[83],"different":[84],"layers,":[85],"targets":[87],"enhances":[89],"specific":[90],"emotion-related":[91],"signals":[92],"from":[93],"intermediate":[94],"that":[96,112],"are":[97],"often":[98],"suppressed":[99],"deeper":[101],"layers.":[102],"Extensive":[103],"experiments":[104],"IEMOCAP":[107],"MELD":[109],"datasets":[110],"demonstrate":[111],"achieves":[114],"better":[115],"performance":[116],"previous":[118],"state-of-the-art":[119],"methods,":[120],"validating":[121],"effectiveness":[123],"enhancing":[125],"intermediate-layer":[126],"SER.":[129]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}