{"id":"https://openalex.org/W4403285040","doi":"https://doi.org/10.1186/s13636-024-00368-0","title":"UTran-DSR: a novel transformer-based model using feature enhancement for dysarthric speech recognition","display_name":"UTran-DSR: a novel transformer-based model using feature enhancement for dysarthric speech recognition","publication_year":2024,"publication_date":"2024-10-11","ids":{"openalex":"https://openalex.org/W4403285040","doi":"https://doi.org/10.1186/s13636-024-00368-0"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-024-00368-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00368-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00368-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00368-0","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023406970","display_name":"Usama Bin Irshad","orcid":"https://orcid.org/0000-0003-4000-3444"},"institutions":[{"id":"https://openalex.org/I173207729","display_name":"University of Engineering and Technology Taxila","ror":"https://ror.org/03v00ka07","country_code":"PK","type":"education","lineage":["https://openalex.org/I173207729"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Usama Irshad","raw_affiliation_strings":["Department of Computer Science, University of Engineering and Technology Taxila, Taxila, 47050, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Engineering and Technology Taxila, Taxila, 47050, Pakistan","institution_ids":["https://openalex.org/I173207729"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039674369","display_name":"Rabbia Mahum","orcid":"https://orcid.org/0000-0003-1983-8201"},"institutions":[{"id":"https://openalex.org/I173207729","display_name":"University of Engineering and Technology Taxila","ror":"https://ror.org/03v00ka07","country_code":"PK","type":"education","lineage":["https://openalex.org/I173207729"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Rabbia Mahum","raw_affiliation_strings":["Department of Computer Science, University of Engineering and Technology Taxila, Taxila, 47050, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Engineering and Technology Taxila, Taxila, 47050, Pakistan","institution_ids":["https://openalex.org/I173207729"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092551472","display_name":"Ismaila Ganiyu","orcid":null},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]},{"id":"https://openalex.org/I4210107237","display_name":"King Salman Center for Disability Research","ror":"https://ror.org/01ht2b307","country_code":"SA","type":"nonprofit","lineage":["https://openalex.org/I4210107237"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ismaila Ganiyu","raw_affiliation_strings":["Industrial Engineering Department, College of Engineering, King Saud University, PO Box 800, Riyadh, 11421, Saudi Arabia","King Salman Center for Disability Research, PO Box 94682 , Riyadh, 11614, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Engineering Department, College of Engineering, King Saud University, PO Box 800, Riyadh, 11421, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]},{"raw_affiliation_string":"King Salman Center for Disability Research, PO Box 94682 , Riyadh, 11614, Saudi Arabia","institution_ids":["https://openalex.org/I4210107237"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012726153","display_name":"Faisal Shafique Butt","orcid":"https://orcid.org/0000-0002-8754-6887"},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Faisal Shafique Butt","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantt, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantt, Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042338791","display_name":"Lotfi Hidri","orcid":"https://orcid.org/0000-0001-6868-7353"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]},{"id":"https://openalex.org/I4210107237","display_name":"King Salman Center for Disability Research","ror":"https://ror.org/01ht2b307","country_code":"SA","type":"nonprofit","lineage":["https://openalex.org/I4210107237"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Lotfi Hidri","raw_affiliation_strings":["Industrial Engineering Department, College of Engineering, King Saud University, PO Box 800, Riyadh, 11421, Saudi Arabia","King Salman Center for Disability Research, PO Box 94682 , Riyadh, 11614, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Engineering Department, College of Engineering, King Saud University, PO Box 800, Riyadh, 11421, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]},{"raw_affiliation_string":"King Salman Center for Disability Research, PO Box 94682 , Riyadh, 11614, Saudi Arabia","institution_ids":["https://openalex.org/I4210107237"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111750135","display_name":"T. Ali","orcid":null},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Tamer G. Ali","raw_affiliation_strings":["Industrial Engineering Department, College of Engineering, King Saud University, PO Box 800, Riyadh, 11421, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Engineering Department, College of Engineering, King Saud University, PO Box 800, Riyadh, 11421, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031572027","display_name":"Ahmed M. El\u2010Sherbeeny","orcid":"https://orcid.org/0000-0003-3559-6249"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]},{"id":"https://openalex.org/I4210107237","display_name":"King Salman Center for Disability Research","ror":"https://ror.org/01ht2b307","country_code":"SA","type":"nonprofit","lineage":["https://openalex.org/I4210107237"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ahmed M. El-Sherbeeny","raw_affiliation_strings":["Industrial Engineering Department, College of Engineering, King Saud University, PO Box 800, Riyadh, 11421, Saudi Arabia","King Salman Center for Disability Research, PO Box 94682 , Riyadh, 11614, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Engineering Department, College of Engineering, King Saud University, PO Box 800, Riyadh, 11421, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]},{"raw_affiliation_string":"King Salman Center for Disability Research, PO Box 94682 , Riyadh, 11614, Saudi Arabia","institution_ids":["https://openalex.org/I4210107237"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5039674369"],"corresponding_institution_ids":["https://openalex.org/I173207729"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.806,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87618397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"2024","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T10863","display_name":"Voice and Speech Disorders","score":0.998199999332428,"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/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.8414458632469177},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.8032732605934143},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6756983399391174},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47176769375801086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3512415289878845},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3488558828830719},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07852116227149963},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.039070725440979004}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8414458632469177},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8032732605934143},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6756983399391174},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47176769375801086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3512415289878845},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3488558828830719},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07852116227149963},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.039070725440979004},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-024-00368-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00368-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00368-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:def87428b45b4bd0977d224a9fa0ba3d","is_oa":false,"landing_page_url":"https://doaj.org/article/def87428b45b4bd0977d224a9fa0ba3d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2024, Iss 1, Pp 1-18 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-024-00368-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00368-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00368-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G739263798","display_name":null,"funder_award_id":"KSRG-2022-136","funder_id":"https://openalex.org/F4320330363","funder_display_name":"King Salman Center for Disability Research"}],"funders":[{"id":"https://openalex.org/F4320330363","display_name":"King Salman Center for Disability Research","ror":"https://ror.org/01ht2b307"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403285040.pdf","grobid_xml":"https://content.openalex.org/works/W4403285040.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1945053386","https://openalex.org/W1990353734","https://openalex.org/W2018363392","https://openalex.org/W2077673009","https://openalex.org/W2084123349","https://openalex.org/W2121486117","https://openalex.org/W2123939933","https://openalex.org/W2142300631","https://openalex.org/W2494741411","https://openalex.org/W2595767284","https://openalex.org/W2892009249","https://openalex.org/W2923997689","https://openalex.org/W2936861580","https://openalex.org/W2937864292","https://openalex.org/W2938757327","https://openalex.org/W2945743426","https://openalex.org/W2962826786","https://openalex.org/W2980844599","https://openalex.org/W3013018143","https://openalex.org/W3015693260","https://openalex.org/W3016093409","https://openalex.org/W3026777299","https://openalex.org/W3097966334","https://openalex.org/W3099550332","https://openalex.org/W3120067823","https://openalex.org/W3174329270","https://openalex.org/W3193618782","https://openalex.org/W4234552385","https://openalex.org/W4247360942","https://openalex.org/W4323315382","https://openalex.org/W4386025707","https://openalex.org/W4386561400","https://openalex.org/W4388622895","https://openalex.org/W4391825007","https://openalex.org/W4392054338","https://openalex.org/W4392984105","https://openalex.org/W4393380737","https://openalex.org/W4399997461","https://openalex.org/W6610385870","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W1992327129","https://openalex.org/W2381986121","https://openalex.org/W2370918718","https://openalex.org/W2256933480","https://openalex.org/W2027854990","https://openalex.org/W2370081953","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Over":[0],"the":[1,4,52,91,97,115,124,130,165,198,207],"past":[2],"decade,":[3],"prevalence":[5],"of":[6,42,54,238],"neurological":[7,32],"diseases":[8],"has":[9],"significantly":[10,214],"risen":[11],"due":[12],"to":[13,150,164,167],"population":[14],"growth":[15],"and":[16,25,40,71,96,107,155,188,201,204,218,224],"aging.":[17],"Individuals":[18],"suffering":[19],"from":[20,36,69],"spastic":[21],"paralysis,":[22],"brain":[23],"attack,":[24],"idiopathic":[26],"Parkinson\u2019s":[27],"disease":[28],"(PD),":[29],"among":[30],"other":[31],"illnesses,":[33],"commonly":[34],"suffer":[35],"dysarthria.":[37],"Early":[38],"detection":[39],"treatment":[41],"dysarthria":[43],"in":[44,129,183,215],"these":[45],"patients":[46],"are":[47],"essential":[48],"for":[49,65],"effectively":[50,104,222],"managing":[51],"progression":[53],"their":[55],"disease.":[56],"This":[57,102],"paper":[58],"provides":[59],"UTrans-DSR,":[60],"a":[61,86,135,147],"novel":[62],"encoder-decoder":[63],"architecture":[64],"analyzing":[66],"Mel-spectrograms":[67],"(generated":[68],"audios)":[70],"classifying":[72,225],"speech":[73,200],"as":[74],"healthy":[75],"or":[76],"dysarthric.":[77],"Our":[78,176],"model":[79,157,212,230],"employs":[80],"transformer":[81,99,132],"encoder":[82],"features":[83],"based":[84,179],"on":[85,180,195],"hybrid":[87],"design,":[88],"which":[89],"includes":[90],"feature":[92,117,169,220],"enhancement":[93],"block":[94],"(FEB)":[95],"vision":[98,131],"(ViT)":[100],"encoders.":[101],"combination":[103],"extracts":[105],"global":[106],"local":[108],"pixel":[109],"information":[110],"regarding":[111],"localization":[112],"while":[113,133,171],"optimizing":[114],"mel-spectrograms":[116,184],"extraction":[118],"process.":[119],"We":[120,159,191],"keep":[121],"up":[122],"with":[123],"original":[125],"class-token":[126],"grouping":[127],"sequence":[128],"generating":[134],"new":[136],"equivalent":[137],"expanding":[138],"route.":[139],"More":[140],"specifically,":[141],"two":[142],"unique":[143],"growing":[144],"pathways":[145],"use":[146],"deep-supervision":[148],"approach":[149],"increase":[151],"spatial":[152,173,219],"data":[153,174],"recovery":[154],"expedite":[156],"convergence.":[158],"add":[160],"consecutive":[161],"residual":[162],"connections":[163],"system":[166],"reduce":[168],"loss":[170],"increasing":[172],"retrieval.":[175],"technique":[177],"is":[178],"identifying":[181],"gaps":[182],"distinguishing":[185],"between":[186],"normal":[187],"dysarthric":[189],"speech.":[190],"conducted":[192],"several":[193],"experiments":[194],"UTrans-DSR":[196],"using":[197],"UA":[199],"TORGO":[202],"datasets,":[203],"it":[205],"outperformed":[206],"existing":[208],"top":[209],"models.":[210],"The":[211,228],"performed":[213],"pixel\u2019s":[216],"localized":[217],"extraction,":[221],"detecting":[223],"spectral":[226],"gaps.":[227],"Tran-DSR":[229],"outperforms":[231],"previous":[232],"research":[233],"models,":[234],"achieving":[235],"an":[236],"accuracy":[237],"97.75%.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-10-10T00:00:00"}
