{"id":"https://openalex.org/W4405709763","doi":"https://doi.org/10.1109/iscslp63861.2024.10800228","title":"Fine-Tuning Pre-Trained Audio Models for Dysarthria Severity Classification: A Second Place Solution in the Multimodal Dysarthria Severity Classification Challenge","display_name":"Fine-Tuning Pre-Trained Audio Models for Dysarthria Severity Classification: A Second Place Solution in the Multimodal Dysarthria Severity Classification Challenge","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709763","doi":"https://doi.org/10.1109/iscslp63861.2024.10800228"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100671165","display_name":"Wei Dai","orcid":"https://orcid.org/0000-0002-8751-7808"},"institutions":[{"id":"https://openalex.org/I4210103616","display_name":"Space (Italy)","ror":"https://ror.org/01c79fd45","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210103616"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Wei Dai","raw_affiliation_strings":["Robo Space"],"affiliations":[{"raw_affiliation_string":"Robo Space","institution_ids":["https://openalex.org/I4210103616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703867","display_name":"Menglong Li","orcid":"https://orcid.org/0000-0002-0033-6933"},"institutions":[{"id":"https://openalex.org/I4210103616","display_name":"Space (Italy)","ror":"https://ror.org/01c79fd45","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210103616"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Menglong Li","raw_affiliation_strings":["Robo Space"],"affiliations":[{"raw_affiliation_string":"Robo Space","institution_ids":["https://openalex.org/I4210103616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065522062","display_name":"Yanxiang He","orcid":"https://orcid.org/0000-0002-8648-993X"},"institutions":[{"id":"https://openalex.org/I4210103616","display_name":"Space (Italy)","ror":"https://ror.org/01c79fd45","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210103616"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Yingqi He","raw_affiliation_strings":["Robo Space"],"affiliations":[{"raw_affiliation_string":"Robo Space","institution_ids":["https://openalex.org/I4210103616"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110363841","display_name":"Yongqiang Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103616","display_name":"Space (Italy)","ror":"https://ror.org/01c79fd45","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210103616"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Yongqiang Zhu","raw_affiliation_strings":["Robo Space"],"affiliations":[{"raw_affiliation_string":"Robo Space","institution_ids":["https://openalex.org/I4210103616"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100671165"],"corresponding_institution_ids":["https://openalex.org/I4210103616"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33962512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9937999844551086,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.9776145219802856},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5820282697677612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5500431060791016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37702399492263794},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.28805816173553467},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.18122780323028564}],"concepts":[{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.9776145219802856},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5820282697677612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5500431060791016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37702399492263794},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.28805816173553467},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.18122780323028564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":7,"referenced_works":["https://openalex.org/W3130967494","https://openalex.org/W4224315877","https://openalex.org/W4297267083","https://openalex.org/W4396843629","https://openalex.org/W4399997461","https://openalex.org/W6862568103","https://openalex.org/W6866580884"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Dysarthria,":[0],"a":[1,146,181],"neurological":[2],"disorder":[3],"affecting":[4],"speech,":[5],"poses":[6],"significant":[7],"challenges":[8,29],"for":[9,86,196],"automatic":[10],"diagnosis":[11],"and":[12,19,57,60,75,92,120,122,151,163,208],"severity":[13,174],"classification":[14],"due":[15],"to":[16,65,68,103,170,212],"its":[17],"complexity":[18],"the":[20,32,36,52,69,81,129,135,142,167,186,189,203],"scarcity":[21],"of":[22,128,149,155,176,191,205],"relevant":[23],"datasets.":[24],"This":[25,99],"study":[26],"addresses":[27],"these":[28],"by":[30,35],"leveraging":[31],"dataset":[33,87],"provided":[34],"ISCSLP":[37],"2024":[38],"Multimodal":[39],"Dysarthria":[40],"Severity":[41],"Classification":[42],"Challenge.":[43],"Our":[44,131,178],"approach":[45,179],"primarily":[46],"involves":[47],"two":[48,115],"key":[49],"steps:":[50],"splitting":[51],"training":[53,56,91],"set":[54],"into":[55],"validation":[58,93,147],"subsets,":[59],"fine-tuning":[61,192],"pre-trained":[62,116,193],"au-dio":[63],"models":[64,195],"adapt":[66],"them":[67,124],"task.":[70,198],"To":[71],"ensure":[72],"robust":[73],"evaluation":[74],"prevent":[76],"label":[77],"leakage,":[78],"we":[79,113],"employed":[80],"StratifiedGroupKFold":[82],"function":[83],"from":[84],"sklearn":[85],"splitting,":[88],"ensuring":[89],"that":[90,134],"sets":[94],"do":[95],"not":[96],"share":[97],"participants.":[98],"method":[100],"allowed":[101],"us":[102],"maintain":[104],"consistent":[105],"statistical":[106],"distributions":[107],"across":[108],"folds.":[109],"For":[110],"model":[111,137,215],"finetuning,":[112],"selected":[114],"audio":[117,194],"models,":[118],"w2v-bert-2.0":[119,136],"whisper-Iarge-v3,":[121],"fine-tuned":[123,138],"on":[125,139],"different":[126,173],"folds":[127],"dataset.":[130],"results":[132],"indicate":[133],"fold-2":[140],"achieved":[141,180],"highest":[143],"performance,":[144],"with":[145],"Fl-score":[148],"0.699":[150],"an":[152],"online":[153],"score":[154],"7.7452.":[156],"The":[157],"experimental":[158],"results,":[159],"including":[160],"confusion":[161],"matrices":[162],"embedding":[164],"distributions,":[165],"highlight":[166],"model's":[168],"ability":[169],"distinguish":[171],"between":[172],"levels":[175],"dysarthria.":[177],"commendable":[182],"second":[183],"place":[184],"in":[185],"competition\u2019":[187],"demonstrating":[188],"effectiveness":[190],"this":[197],"Future":[199],"work":[200],"will":[201],"explore":[202],"integration":[204],"multimodal":[206],"data":[207],"multi-task":[209],"learning":[210],"strategies":[211],"further":[213],"enhance":[214],"performance.":[216]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}