{"id":"https://openalex.org/W7142658930","doi":"https://doi.org/10.1016/j.specom.2026.103393","title":"Diagnosis-aware multitask fine-tuning of Whisper for dysarthric speech recognition","display_name":"Diagnosis-aware multitask fine-tuning of Whisper for dysarthric speech recognition","publication_year":2026,"publication_date":"2026-03-29","ids":{"openalex":"https://openalex.org/W7142658930","doi":"https://doi.org/10.1016/j.specom.2026.103393"},"language":"en","primary_location":{"id":"doi:10.1016/j.specom.2026.103393","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2026.103393","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.specom.2026.103393","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130908935","display_name":"Yoona Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoona Chung","raw_affiliation_strings":["Department of Information Systems, College of Engineering, Hanyang University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0003-8487-5743","affiliations":[{"raw_affiliation_string":"Department of Information Systems, College of Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130885382","display_name":"Jeongmin Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongmin Hong","raw_affiliation_strings":["Department of Information Systems, College of Engineering, Hanyang University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, College of Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130890021","display_name":"Jaehyuk Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]},{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehyuk Lee","raw_affiliation_strings":["Department of Information Systems, College of Engineering, Hanyang University, Seoul, South Korea","Institute of IT Convergence Technology, Seoul National University of Science and Technology, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, College of Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Institute of IT Convergence Technology, Seoul National University of Science and Technology, Seoul, South Korea","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130899069","display_name":"Eunchan Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Eunchan Kim","raw_affiliation_strings":["Department of Artificial Intelligence, College of Engineering, Hanyang University, Seoul, South Korea","Department of Information Systems, College of Engineering, Hanyang University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-3743-3550","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, College of Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Information Systems, College of Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5130899069"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":{"value":2900,"currency":"USD","value_usd":2900},"apc_paid":{"value":2900,"currency":"USD","value_usd":2900},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28304455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"180","issue":null,"first_page":"103393","last_page":"103393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.6105999946594238,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.6105999946594238,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.1454000025987625,"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/T10860","display_name":"Speech and Audio Processing","score":0.041099999099969864,"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/dysarthria","display_name":"Dysarthria","score":0.45750001072883606},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4059000015258789},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3517000079154968},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.34610000252723694},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3188000023365021}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7335000038146973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027000188827515},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4059000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39570000767707825},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3264999985694885},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.specom.2026.103393","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2026.103393","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.specom.2026.103393","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2026.103393","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5733130164","display_name":null,"funder_award_id":"HY-202500000001616","funder_id":"https://openalex.org/F4320321142","funder_display_name":"Hanyang University"},{"id":"https://openalex.org/G7767329031","display_name":null,"funder_award_id":"RS-2023-00275579","funder_id":"https://openalex.org/F4320321408","funder_display_name":"Ministry of Education"}],"funders":[{"id":"https://openalex.org/F4320321142","display_name":"Hanyang University","ror":"https://ror.org/046865y68"},{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1541019354","https://openalex.org/W1678356000","https://openalex.org/W1980345827","https://openalex.org/W2037533540","https://openalex.org/W2063066213","https://openalex.org/W2071128523","https://openalex.org/W2089337869","https://openalex.org/W2095660652","https://openalex.org/W2129120544","https://openalex.org/W2136492531","https://openalex.org/W2144683894","https://openalex.org/W2167009007","https://openalex.org/W2182621190","https://openalex.org/W2191779130","https://openalex.org/W2346340151","https://openalex.org/W2554388195","https://openalex.org/W2793398224","https://openalex.org/W2884225676","https://openalex.org/W2887725488","https://openalex.org/W2897880775","https://openalex.org/W2903950532","https://openalex.org/W2911964244","https://openalex.org/W2951936533","https://openalex.org/W3011397292","https://openalex.org/W3011512709","https://openalex.org/W3022666696","https://openalex.org/W3091427154","https://openalex.org/W3118747422","https://openalex.org/W3216191787","https://openalex.org/W4221162789","https://openalex.org/W4223646484","https://openalex.org/W4225274058","https://openalex.org/W4324135725","https://openalex.org/W4379013055","https://openalex.org/W4390906198","https://openalex.org/W4395661434","https://openalex.org/W4401359134","https://openalex.org/W4402639795","https://openalex.org/W4402828530","https://openalex.org/W4406991784","https://openalex.org/W4407784341","https://openalex.org/W4408126038","https://openalex.org/W4408591655","https://openalex.org/W4409417224","https://openalex.org/W4409595275","https://openalex.org/W4410204238"],"related_works":[],"abstract_inverted_index":{"Individuals":[0],"with":[1,116,174],"dysarthria":[2],"exhibit":[3],"irregular":[4],"speech":[5,53,155,170],"patterns":[6],"that":[7,92,149,165],"vary":[8],"by":[9,107,137],"disease,":[10],"significantly":[11],"reducing":[12],"the":[13,66,77,84,105,117,125,133,159],"accuracy":[14],"of":[15,76,131,161],"conventional":[16],"speech-recognition":[17,79,163],"systems.":[18],"Previous":[19],"studies":[20],"have":[21],"typically":[22],"focused":[23],"on":[24,71,95,124],"a":[25,50,121],"single":[26],"disease":[27,57],"group":[28],"or":[29],"used":[30],"aggregated":[31],"data":[32],"without":[33],"accounting":[34],"for":[35],"inter-disease":[36],"variation,":[37],"thereby":[38],"limiting":[39],"disease-specific":[40,78,102,150],"insights.":[41],"In":[42,129],"this":[43],"study,":[44],"fluency":[45,96],"metrics":[46,97],"were":[47,68],"extracted":[48],"from":[49],"Korean":[51],"dysarthric":[52],"corpus":[54],"across":[55],"three":[56],"groups":[58],"(stroke,":[59],"cerebral":[60],"palsy,":[61],"and":[62,65,111,120,141,157],"peripheral":[63],"neuropathy)":[64],"diseases":[67],"classified":[69],"based":[70,94],"these":[72],"features.":[73],"The":[74,101],"performance":[75],"models":[80,103,151],"was":[81],"evaluated":[82],"using":[83],"weighted":[85],"character":[86],"error":[87,134],"rate":[88,135],"(Weighted-CER).":[89],"Results":[90],"showed":[91],"classification":[93],"achieved":[98],"99%":[99],"accuracy.":[100],"improved":[104],"CER":[106],"up":[108,138],"to":[109,139,168],"18.34":[110],"1.05":[112],"percentage":[113,143],"points":[114],"compared":[115],"Whisper\u2013Small":[118],"model":[119,122],"trained":[123],"entire":[126],"dataset,":[127],"respectively.":[128,145],"terms":[130],"Weighted-CER,":[132],"decreased":[136],"15.27":[140],"1.49":[142],"points,":[144],"These":[146],"findings":[147],"indicate":[148],"can":[152,166],"meaningfully":[153],"enhance":[154],"recognition":[156],"underscore":[158],"importance":[160],"developing":[162],"systems":[164],"adapt":[167],"individual":[169],"characteristics":[171],"in":[172],"patients":[173],"dysarthria.":[175]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-03-30T00:00:00"}
