{"id":"https://openalex.org/W7148419550","doi":"https://doi.org/10.1109/asru65441.2025.11434603","title":"Robust Speech Emotion Recognition via Classifier Retraining on Mixup-Augmented Representations","display_name":"Robust Speech Emotion Recognition via Classifier Retraining on Mixup-Augmented Representations","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148419550","doi":"https://doi.org/10.1109/asru65441.2025.11434603"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434603","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/A5071262282","display_name":"Shi-wook Lee","orcid":"https://orcid.org/0000-0002-2377-6376"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shi-Wook Lee","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071262282"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8191238,"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":0.9212999939918518,"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":0.9212999939918518,"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":0.011699999682605267,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.011300000362098217,"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/emotion-recognition","display_name":"Emotion recognition","score":0.5152999758720398},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5033000111579895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34779998660087585},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3237999975681305},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3109999895095825},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.2924000024795532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6176000237464905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5814999938011169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5633999705314636},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2572000026702881},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434603","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2342475039","https://openalex.org/W2611652970","https://openalex.org/W2891021639","https://openalex.org/W3174770825","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W4307823382"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"proposes":[2],"a":[3],"novel":[4],"augmentation":[5],"framework":[6],"for":[7],"speech":[8,119],"emotion":[9,120],"recognition":[10],"that":[11,51],"enhances":[12],"robustness":[13],"and":[14,31,57,63,85,103],"generalization":[15,109],"by":[16],"retraining":[17],"the":[18,25,41,53,59,73,81,97],"classifier":[19],"on":[20,117],"Mixupaugmented":[21],"representations.":[22],"We":[23],"leverage":[24],"complementarity":[26],"of":[27,61],"representations":[28,47,50,68],"from":[29,89],"full":[30],"top":[32],"fine-tuning":[33,91],"strategies,":[34],"which":[35],"capture":[36],"distinct":[37],"emotional":[38,104],"cues.":[39],"Applying":[40],"Mixup":[42],"technique":[43],"across":[44],"these":[45],"heterogeneous":[46],"produces":[48],"interpolated":[49,67],"enrich":[52],"original":[54],"representation":[55,83],"spaces":[56],"support":[58],"learning":[60],"various":[62],"discriminative":[64],"patterns.":[65],"These":[66],"are":[69],"used":[70],"to":[71,78,80,100,107],"retrain":[72],"final":[74],"classifier,":[75],"enabling":[76],"it":[77],"adapt":[79],"expanded":[82],"space":[84],"effectively":[86],"integrate":[87],"information":[88],"both":[90],"perspectives.":[92],"The":[93,113],"proposed":[94],"process":[95],"improves":[96],"model\u2019s":[98],"ability":[99],"handle":[101],"acoustic":[102],"variability,":[105],"leading":[106],"improved":[108],"under":[110],"domain":[111],"shifts.":[112],"method":[114],"is":[115],"validated":[116],"four":[118],"datasets":[121],"covering":[122],"two":[123],"languages.":[124]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}