{"id":"https://openalex.org/W7148260033","doi":"https://doi.org/10.1109/asru65441.2025.11434684","title":"CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition","display_name":"CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148260033","doi":"https://doi.org/10.1109/asru65441.2025.11434684"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434684","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":null,"display_name":"Yun-Shao Tsai","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yun-Shao Tsai","raw_affiliation_strings":["National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083437044","display_name":"Yi\u2010Cheng Lin","orcid":"https://orcid.org/0000-0002-5130-5280"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Cheng Lin","raw_affiliation_strings":["National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089273852","display_name":"Huang-Cheng Chou","orcid":"https://orcid.org/0000-0003-2125-5689"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang-Cheng Chou","raw_affiliation_strings":["University of Southern California,Los Angeles,California,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,California,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132807525","display_name":"Hung-Yi Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80448607,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.7918000221252441,"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":0.7918000221252441,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.09220000356435776,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.010099999606609344,"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/debiasing","display_name":"Debiasing","score":0.972100019454956},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5782999992370605},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.51910001039505},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4684000015258789},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4156999886035919},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4147999882698059}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.972100019454956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6385999917984009},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5892999768257141},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4526999890804291},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4514000117778778},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.36340001225471497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34850001335144043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33390000462532043},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2653000056743622}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434684","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":[{"score":0.4507914185523987,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1480450040","https://openalex.org/W2030931454","https://openalex.org/W2150593711","https://openalex.org/W2164089264","https://openalex.org/W2342475039","https://openalex.org/W2555370706","https://openalex.org/W2607719644","https://openalex.org/W2742542661","https://openalex.org/W2962684181","https://openalex.org/W2972935927","https://openalex.org/W3024869864","https://openalex.org/W3035139434","https://openalex.org/W3197580070","https://openalex.org/W3198806843","https://openalex.org/W3203690435","https://openalex.org/W3206559778","https://openalex.org/W3209984917","https://openalex.org/W3212216134","https://openalex.org/W4224920133","https://openalex.org/W4280599741","https://openalex.org/W4296068794","https://openalex.org/W4296069263","https://openalex.org/W4296069354","https://openalex.org/W4311404391","https://openalex.org/W4313444088","https://openalex.org/W4372260053","https://openalex.org/W4372270707","https://openalex.org/W4381786694","https://openalex.org/W4385571404","https://openalex.org/W4385573723","https://openalex.org/W4385823176","https://openalex.org/W4385823264","https://openalex.org/W4385823432","https://openalex.org/W4387846604","https://openalex.org/W4389520470","https://openalex.org/W4390905977","https://openalex.org/W4391021580","https://openalex.org/W4392903879","https://openalex.org/W4392904806","https://openalex.org/W4399426079","https://openalex.org/W4401043250","https://openalex.org/W4402112074","https://openalex.org/W4402112098","https://openalex.org/W4402112332","https://openalex.org/W4402112334","https://openalex.org/W4402112459","https://openalex.org/W4404518524","https://openalex.org/W4404783105","https://openalex.org/W4406461433","https://openalex.org/W4406461701","https://openalex.org/W4406461890","https://openalex.org/W4408100346","https://openalex.org/W4408345915","https://openalex.org/W4408353897","https://openalex.org/W4408354270","https://openalex.org/W4415433706","https://openalex.org/W4416963454"],"related_works":[],"abstract_inverted_index":{"Bias":[0],"in":[1,69,96,130],"speech":[2],"emotion":[3],"recognition":[4],"(SER)":[5],"systems":[6],"often":[7],"stems":[8],"from":[9,93],"spurious":[10],"correlations":[11],"between":[12],"speaker":[13,89],"characteristics":[14],"and":[15,73,82,116,124],"emotional":[16],"labels,":[17],"leading":[18],"to":[19,78,102],"unfair":[20],"predictions":[21],"across":[22],"demographic":[23,33,58],"groups.":[24],"Many":[25],"existing":[26],"debiasing":[27],"methods":[28],"require":[29],"model-specific":[30],"changes":[31],"or":[32,55],"annotations,":[34],"limiting":[35],"their":[36],"practical":[37,125],"use.":[38],"We":[39],"present":[40,68],"COVADA,":[41],"a":[42,122],"Confidence-Oriented":[43],"Voice":[44],"Augmentation":[45],"Debiasing":[46],"Approach":[47],"that":[48,64,91],"mitigates":[49],"bias":[50,66],"without":[51],"modifying":[52],"model":[53,101],"architecture":[54],"relying":[56],"on":[57,105],"information.":[59],"CO-VADA":[60],"identifies":[61],"training":[62,71],"samples":[63,87],"reflect":[65],"patterns":[67,95],"the":[70,97,100],"data":[72],"then":[74],"applies":[75],"voice":[76,117],"conversion":[77,118],"alter":[79],"irrelevant":[80],"attributes":[81],"generate":[83],"samples.":[84],"These":[85],"augmented":[86],"introduce":[88],"variations":[90],"differ":[92],"dominant":[94],"data,":[98],"guiding":[99],"focus":[103],"more":[104],"emotion-relevant":[106],"features.":[107],"Our":[108],"framework":[109],"is":[110],"compatible":[111],"with":[112],"various":[113],"SER":[114,131],"models":[115],"tools,":[119],"making":[120],"it":[121],"scalable":[123],"solution":[126],"for":[127],"improving":[128],"fairness":[129],"systems.":[132]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-04-03T00:00:00"}