{"id":"https://openalex.org/W4411574865","doi":"https://doi.org/10.32604/cmc.2025.066322","title":"Enhancing Phoneme Labeling in Dysarthric Speech with Digital Twin-Driven Multi-Modal Architecture","display_name":"Enhancing Phoneme Labeling in Dysarthric Speech with Digital Twin-Driven Multi-Modal Architecture","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411574865","doi":"https://doi.org/10.32604/cmc.2025.066322"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.066322","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.066322","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials &amp; Continua","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.32604/cmc.2025.066322","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066924300","display_name":"Saeed Alzahrani","orcid":"https://orcid.org/0000-0003-3325-857X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Saeed Alzahrani","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Nazar Hussain","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nazar Hussain","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012846152","display_name":"Farah Mohammad","orcid":"https://orcid.org/0000-0002-4845-1156"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farah Mohammad","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066924300"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1891278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"84","issue":"3","first_page":"4825","last_page":"4849"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9882000088691711,"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":0.9882000088691711,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9704999923706055,"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":0.963100016117096,"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/speech-recognition","display_name":"Speech recognition","score":0.6150941848754883},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5787611603736877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5772337913513184},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5127943158149719},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.4673754572868347},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.3500010371208191},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2197330892086029},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.11898460984230042}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6150941848754883},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5787611603736877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5772337913513184},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5127943158149719},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.4673754572868347},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3500010371208191},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2197330892086029},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.11898460984230042},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.32604/cmc.2025.066322","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.066322","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials &amp; Continua","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.32604/cmc.2025.066322","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.066322","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials &amp; Continua","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.5099999904632568,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1995516199","https://openalex.org/W2019657476","https://openalex.org/W2109023847","https://openalex.org/W2134315375","https://openalex.org/W3119996911","https://openalex.org/W3157063407","https://openalex.org/W4200093745","https://openalex.org/W4281764283","https://openalex.org/W4313826088","https://openalex.org/W4321368667","https://openalex.org/W4321486452","https://openalex.org/W4323315382","https://openalex.org/W4327544674","https://openalex.org/W4360993686","https://openalex.org/W4364352397","https://openalex.org/W4383819211","https://openalex.org/W4385823120","https://openalex.org/W4387672817","https://openalex.org/W4395661434","https://openalex.org/W4396664303","https://openalex.org/W4399714615","https://openalex.org/W4400929850","https://openalex.org/W4411119439"],"related_works":["https://openalex.org/W2331173358","https://openalex.org/W2969484279","https://openalex.org/W3160456149","https://openalex.org/W2168872498","https://openalex.org/W4400873482","https://openalex.org/W2329762060","https://openalex.org/W2517018229","https://openalex.org/W2351669973","https://openalex.org/W2312964388","https://openalex.org/W2980869992"],"abstract_inverted_index":{"Digital":[0],"twin":[1],"technology":[2,299],"is":[3,67],"revolutionizing":[4],"personalized":[5,50],"healthcare":[6],"by":[7,69],"creating":[8],"dynamic":[9,210],"virtual":[10],"replicas":[11],"of":[12,34,98,133,152,212,259,264,270,280],"individual":[13],"patients.":[14],"This":[15],"paper":[16],"presents":[17],"a":[18,119,131,145],"novel":[19,120],"multi-modal":[20,121],"architecture":[21,122],"leveraging":[22],"digital":[23],"twins":[24],"to":[25,80,93,102,160,177,193],"enhance":[26],"precision":[27,290],"in":[28,167,296],"predictive":[29],"diagnostics":[30],"and":[31,44,59,74,108,127,144,157,164,188,206,243,266,277],"treatment":[32,56],"planning":[33],"phoneme":[35,75,99,104,223,288],"labeling.":[36],"By":[37,272],"integrating":[38],"real-time":[39],"images,":[40],"electronic":[41],"health":[42],"records,":[43],"genomic":[45],"information,":[46],"the":[47,95,153,168,172,185,191,203,213,253,275],"system":[48],"enables":[49],"simulations":[51],"for":[52,300],"disease":[53],"progression":[54],"modeling,":[55],"response":[57],"prediction,":[58],"preventive":[60],"care":[61],"strategies.":[62],"In":[63],"dysarthric":[64],"speech,":[65,281],"which":[66,220],"characterized":[68],"articulation":[70],"imprecision,":[71],"temporal":[72],"misalignments,":[73],"distortions,":[76],"existing":[77,231],"models":[78],"struggle":[79],"capture":[81,161],"these":[82,115],"irregularities.":[83],"Traditional":[84],"approaches,":[85],"often":[86],"relying":[87],"solely":[88],"on":[89,217],"audio":[90,126,150,169,205],"features,":[91,208],"fail":[92],"address":[94],"full":[96],"complexity":[97],"variations,":[100],"leading":[101],"increased":[103],"error":[105,110],"rates":[106,111],"(PER)":[107],"word":[109],"(WER).":[112],"To":[113],"overcome":[114],"challenges,":[116],"we":[117],"propose":[118],"that":[123],"integrates":[124],"both":[125,162,274],"articulatory":[128,173,196,207,278],"data":[129],"through":[130],"combination":[132],"Temporal":[134],"Convolutional":[135,139],"Networks":[136,140],"(TCNs),":[137],"Graph":[138],"(GCNs),":[141],"Transformer":[142,158],"Encoders,":[143],"cross-modal":[146,199],"attention":[147,200],"mechanism.":[148],"The":[149,226],"branch":[151,174],"model":[154,178,192,228,254],"utilizes":[155],"TCNs":[156],"Encoders":[159],"short-":[163],"long-term":[165],"dependencies":[166],"signal,":[170],"while":[171],"leverages":[175],"GCNs":[176],"spatial":[179],"relationships":[180],"between":[181],"articulators,":[182],"such":[183],"as":[184],"lips,":[186],"jaw,":[187],"tongue,":[189],"allowing":[190],"detect":[194],"subtle":[195],"imprecisions.":[197],"A":[198],"mechanism":[201],"fuses":[202],"encoded":[204],"enabling":[209],"adjustment":[211],"model\u2019s":[214],"focus":[215],"depending":[216],"input":[218],"quality,":[219],"significantly":[221],"improves":[222,287],"labeling":[224,289],"accuracy.":[225],"proposed":[227],"consistently":[229],"outperforms":[230],"methods,":[232],"achieving":[233],"lower":[234],"Phoneme":[235],"Error":[236,240],"Rates":[237,241,247],"(PER),":[238],"Word":[239],"(WER),":[242],"Articulatory":[244],"Feature":[245],"Misclassification":[246],"(AFMR).":[248],"Specifically,":[249],"across":[250],"all":[251],"datasets,":[252],"achieves":[255],"an":[256,261,267],"average":[257,262,268],"PER":[258],"13.43%,":[260],"WER":[263],"21.67%,":[265],"AFMR":[269],"12.73%.":[271],"capturing":[273],"acoustic":[276],"intricacies":[279],"this":[282],"comprehensive":[283],"approach":[284],"not":[285],"only":[286],"but":[291],"also":[292],"marks":[293],"substantial":[294],"progress":[295],"speech":[297],"recognition":[298],"individuals":[301],"with":[302],"dysarthria.":[303]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
