{"id":"https://openalex.org/W4416800023","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249149","title":"Self-Supervised Learning for Classification of Normal vs. Dysarthric Speech","display_name":"Self-Supervised Learning for Classification of Normal vs. Dysarthric Speech","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416800023","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249149"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5052275368","display_name":"Hiya Chaudhari","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hiya Chaudhari","raw_affiliation_strings":["Dhirubhai Ambani University, (Formerly known as DA-IICT)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University, (Formerly known as DA-IICT)","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103582248","display_name":"Kavya Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kavya Kumar","raw_affiliation_strings":["Dhirubhai Ambani University, (Formerly known as DA-IICT)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University, (Formerly known as DA-IICT)","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113880393","display_name":"Hemant A. Patil","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Dhirubhai Ambani University, (Formerly known as DA-IICT)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani University, (Formerly known as DA-IICT)","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41102457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1010","last_page":"1015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9912999868392944,"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":0.9912999868392944,"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/T11358","display_name":"Dysphagia Assessment and Management","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.0010999999940395355,"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/vowel","display_name":"Vowel","score":0.5555999875068665},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.5048999786376953},{"id":"https://openalex.org/keywords/amyotrophic-lateral-sclerosis","display_name":"Amyotrophic lateral sclerosis","score":0.5005999803543091},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4627000093460083},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4203000068664551},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34459999203681946},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.33090001344680786},{"id":"https://openalex.org/keywords/speech-disorder","display_name":"Speech disorder","score":0.3156000077724457}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6258999705314636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5734000205993652},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5555999875068665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5108000040054321},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C2780596555","wikidata":"https://www.wikidata.org/wiki/Q206901","display_name":"Amyotrophic lateral sclerosis","level":3,"score":0.5005999803543091},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4627000093460083},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C2779642007","wikidata":"https://www.wikidata.org/wiki/Q1282114","display_name":"Speech disorder","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C2777003509","wikidata":"https://www.wikidata.org/wiki/Q6026322","display_name":"Connected speech","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C3018392663","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Speech sound","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320325255","display_name":"Ministry of Electronics and Information technology","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2026895213","https://openalex.org/W2798571323","https://openalex.org/W3117926103","https://openalex.org/W3196525293","https://openalex.org/W3197642003","https://openalex.org/W3213029956","https://openalex.org/W4297841875","https://openalex.org/W4312120782","https://openalex.org/W4321636063","https://openalex.org/W4372338196","https://openalex.org/W4385823241","https://openalex.org/W4400615995","https://openalex.org/W4400834464","https://openalex.org/W4402111659","https://openalex.org/W4402115960","https://openalex.org/W4402454427","https://openalex.org/W4404031868","https://openalex.org/W4405709855","https://openalex.org/W4407561026"],"related_works":[],"abstract_inverted_index":{"Parkinson's":[0,99],"Disease":[1],"(PD)":[2],"and":[3,15,28,37,48,64,66,70,101,110],"Amyotrophic":[4],"Lateral":[5],"Sclerosis":[6],"(ALS)":[7],"are":[8,73],"progressive":[9],"neurodegenerative":[10],"disorders":[11],"that":[12],"cause":[13],"motor":[14],"non-motor":[16],"symptoms,":[17],"including":[18],"dysarthria.":[19],"Their":[20],"early":[21],"detection":[22,39],"is":[23],"crucial":[24],"for":[25,112],"effective":[26],"management":[27],"improved":[29],"quality":[30],"of":[31,119],"life.":[32],"This":[33],"study":[34],"explores":[35],"PD":[36],"ALS":[38],"using":[40,57],"self-supervised":[41],"learning":[42],"(SSL)":[43],"methods":[44],"namely,":[45],"XLS-R,":[46],"HuBERT,":[47],"wav2vec":[49],"2.0.":[50],"We":[51],"analyze":[52],"normal":[53],"vs.":[54],"dysarthric":[55],"speech":[56,77],"vowel":[58],"space":[59],"distribution":[60],"plots":[61],"in":[62],"2D":[63],"3D,":[65],"t-SNE":[67],"visualizations.":[68],"BiLSTM":[69],"CNN":[71],"models":[72],"employed":[74],"to":[75,114],"classify":[76],"features,":[78],"comparing":[79],"XLS-R":[80,122],"300M":[81,123],"with":[82],"other":[83],"pre-trained":[84],"models.":[85],"Our":[86],"approach":[87],"achieves":[88],"an":[89],"8.25":[90],"%":[91],"improvement":[92],"over":[93],"wave2vec":[94],"2.0":[95],"on":[96],"the":[97,116],"Italian":[98],"Dataset":[100],"VOC-ALS.":[102],"Additionally,":[103],"we":[104],"assess":[105],"latency":[106],"period,":[107],"noise":[108],"robustness,":[109],"precision":[111],"retraining":[113],"evaluate":[115],"practical":[117],"applicability":[118],"relatively":[120],"best":[121],"features.":[124]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}