{"id":"https://openalex.org/W4408352349","doi":"https://doi.org/10.1109/icassp49660.2025.10889515","title":"A Multi-modal Approach to Dysarthria Detection and Severity Assessment Using Speech and Text Information","display_name":"A Multi-modal Approach to Dysarthria Detection and Severity Assessment Using Speech and Text Information","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352349","doi":"https://doi.org/10.1109/icassp49660.2025.10889515"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5098822664","display_name":"M Anuprabha","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anuprabha M","raw_affiliation_strings":["International Institute of Information Technology-Hyderabad,LTRC,India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology-Hyderabad,LTRC,India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014128331","display_name":"Krishna Gurugubelli","orcid":"https://orcid.org/0000-0002-7658-065X"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Krishna Gurugubelli","raw_affiliation_strings":["Samsung Research & Development Institute-Bengaluru,India"],"affiliations":[{"raw_affiliation_string":"Samsung Research & Development Institute-Bengaluru,India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095045867","display_name":"V Kesavaraj","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kesavaraj V","raw_affiliation_strings":["International Institute of Information Technology-Hyderabad,LTRC,India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology-Hyderabad,LTRC,India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007569113","display_name":"Anil Kumar Vuppala","orcid":"https://orcid.org/0000-0001-7795-0408"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anil Kumar Vuppala","raw_affiliation_strings":["International Institute of Information Technology-Hyderabad,LTRC,India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology-Hyderabad,LTRC,India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5098822664"],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":1.1309,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74828039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9761999845504761,"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":0.9761999845504761,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.9480464458465576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7227823734283447},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7063493132591248},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5650346279144287},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47055816650390625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37648385763168335},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.13028717041015625},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.12084227800369263}],"concepts":[{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.9480464458465576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7227823734283447},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7063493132591248},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5650346279144287},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47055816650390625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37648385763168335},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.13028717041015625},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.12084227800369263},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W98096188","https://openalex.org/W180052447","https://openalex.org/W2091380405","https://openalex.org/W2189351760","https://openalex.org/W2744046280","https://openalex.org/W2938626858","https://openalex.org/W2982534039","https://openalex.org/W3015238377","https://openalex.org/W3016093409","https://openalex.org/W3016192394","https://openalex.org/W3092178525","https://openalex.org/W3123500774","https://openalex.org/W4224315877","https://openalex.org/W4224861836","https://openalex.org/W4317748907","https://openalex.org/W4318542802","https://openalex.org/W4372338196","https://openalex.org/W4385245566","https://openalex.org/W4385823241","https://openalex.org/W4389752793","https://openalex.org/W4391825007","https://openalex.org/W4408565113","https://openalex.org/W6679434410"],"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/W3204019825"],"abstract_inverted_index":{"Automatic":[0],"detection":[1,72,138],"and":[2,35,47,52,73,90,94,96,106,109,139],"severity":[3,64,74,99],"assessment":[4,100],"of":[5,70,88],"dysarthria":[6],"are":[7,113],"crucial":[8],"for":[9,98,136],"delivering":[10],"targeted":[11],"therapeutic":[12],"interventions":[13],"to":[14,144],"patients.":[15],"While":[16],"most":[17],"existing":[18],"research":[19],"focuses":[20],"primarily":[21],"on":[22],"speech":[23,34,51],"modality,":[24],"this":[25],"study":[26],"introduces":[27],"a":[28,125,129],"novel":[29],"approach":[30,56],"that":[31,118],"leverages":[32],"both":[33],"text":[36,53,121],"modalities.":[37],"By":[38],"employing":[39],"cross-attention":[40],"mechanism,":[41],"our":[42],"method":[43],"learns":[44],"the":[45,59,68,77],"acoustic":[46],"linguistic":[48,127],"similarities":[49],"between":[50],"representations.":[54],"This":[55],"assesses":[57],"specifically":[58],"pronunciation":[60],"deviations":[61],"across":[62],"different":[63],"levels,":[65],"thereby":[66,141],"enhancing":[67],"accuracy":[69],"dysarthric":[71,84,137],"assessment.":[75],"All":[76],"experiments":[78],"have":[79,101],"been":[80,102,134],"performed":[81],"using":[82],"UA-Speech":[83],"database.":[85],"Improved":[86],"accuracies":[87],"99.53%":[89],"93.20%":[91],"in":[92],"detection,":[93],"98.12%":[95],"51.97%":[97],"achieved":[103],"when":[104],"speaker-dependent":[105],"speaker-independent,":[107],"unseen":[108],"seen":[110],"words":[111],"settings":[112],"used.":[114],"These":[115],"findings":[116],"suggest":[117],"by":[119],"integrating":[120],"information,":[122],"which":[123],"provides":[124],"reference":[126],"knowledge,":[128],"more":[130,145],"robust":[131],"framework":[132],"has":[133],"developed":[135],"assessment,":[140],"potentially":[142],"leading":[143],"effective":[146],"diagnoses.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}