{"id":"https://openalex.org/W4410342580","doi":"https://doi.org/10.1109/ncc63735.2025.10983605","title":"Enhancing Traditional Kaldi Dysarthric Speech Recognition Using SSL-Features","display_name":"Enhancing Traditional Kaldi Dysarthric Speech Recognition Using SSL-Features","publication_year":2025,"publication_date":"2025-03-06","ids":{"openalex":"https://openalex.org/W4410342580","doi":"https://doi.org/10.1109/ncc63735.2025.10983605"},"language":"en","primary_location":{"id":"doi:10.1109/ncc63735.2025.10983605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc63735.2025.10983605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 National Conference on Communications (NCC)","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/A5106638699","display_name":"Paban Sapkota","orcid":null},"institutions":[{"id":"https://openalex.org/I101326570","display_name":"National Institute of Technology Sikkim","ror":"https://ror.org/04pam3b03","country_code":"IN","type":"education","lineage":["https://openalex.org/I101326570"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Paban Sapkota","raw_affiliation_strings":["National Institute of Technology,Department of Electronics and Communication Engineering,Sikkim,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Department of Electronics and Communication Engineering,Sikkim,India","institution_ids":["https://openalex.org/I101326570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101748731","display_name":"Abhijit Sinha","orcid":"https://orcid.org/0000-0003-3264-6319"},"institutions":[{"id":"https://openalex.org/I101326570","display_name":"National Institute of Technology Sikkim","ror":"https://ror.org/04pam3b03","country_code":"IN","type":"education","lineage":["https://openalex.org/I101326570"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhijit Sinha","raw_affiliation_strings":["National Institute of Technology,Department of Electronics and Communication Engineering,Sikkim,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Department of Electronics and Communication Engineering,Sikkim,India","institution_ids":["https://openalex.org/I101326570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003438160","display_name":"Hemant Kumar Kathania","orcid":"https://orcid.org/0000-0002-6367-5203"},"institutions":[{"id":"https://openalex.org/I101326570","display_name":"National Institute of Technology Sikkim","ror":"https://ror.org/04pam3b03","country_code":"IN","type":"education","lineage":["https://openalex.org/I101326570"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant Kumar Kathania","raw_affiliation_strings":["National Institute of Technology,Department of Electronics and Communication Engineering,Sikkim,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Department of Electronics and Communication Engineering,Sikkim,India","institution_ids":["https://openalex.org/I101326570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080870546","display_name":"Sudarsana Reddy Kadiri","orcid":"https://orcid.org/0000-0001-5806-3053"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudarsana Reddy Kadiri","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory (SAIL),Los Angeles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory (SAIL),Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5106638699"],"corresponding_institution_ids":["https://openalex.org/I101326570"],"apc_list":null,"apc_paid":null,"fwci":4.0602,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.93538425,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.972599983215332,"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":0.972599983215332,"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":0.9611999988555908,"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":0.9319999814033508,"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/computer-science","display_name":"Computer science","score":0.7229308485984802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7131211161613464},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46206697821617126},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4394175112247467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33962225914001465},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3000519275665283}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229308485984802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7131211161613464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46206697821617126},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4394175112247467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33962225914001465},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3000519275665283}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ncc63735.2025.10983605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc63735.2025.10983605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W1988536708","https://openalex.org/W2045644151","https://openalex.org/W2888867175","https://openalex.org/W2936861580","https://openalex.org/W2938757327","https://openalex.org/W3014690389","https://openalex.org/W3015210890","https://openalex.org/W3015611303","https://openalex.org/W3163599377","https://openalex.org/W3209059054","https://openalex.org/W4297030419","https://openalex.org/W4297841798","https://openalex.org/W4321500171","https://openalex.org/W4323315382","https://openalex.org/W4386025707","https://openalex.org/W4387672817","https://openalex.org/W4392909075","https://openalex.org/W4401752236","https://openalex.org/W6631362777","https://openalex.org/W6780218876","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841"],"abstract_inverted_index":{"Dysarthric":[0],"speech":[1],"poses":[2],"significant":[3],"challenges":[4],"for":[5,38,110,137],"automated":[6],"recognition":[7],"systems,":[8],"which":[9],"perform":[10],"well":[11],"with":[12],"normal":[13],"speech.":[14,40,139],"This":[15],"paper":[16],"investigates":[17],"the":[18,57,75,78,95,111],"adaptation":[19],"of":[20,102],"embeddings":[21],"from":[22,56],"large":[23],"self-supervised":[24],"learning":[25],"(SSL)":[26],"models\u2014Wav2Vec2,":[27],"HuBERT,":[28],"and":[29,34,50,87,104,113],"Data2Vec\u2014to":[30],"traditional":[31],"Kaldi-based":[32],"DNN/HMM":[33],"Factorized-TDNN":[35],"ASR":[36,54,135],"systems":[37,42,136],"dysarthric":[39,138],"Baseline":[41],"were":[43,62],"developed":[44],"using":[45,121,131],"MFCC":[46],"features,":[47],"ensuring":[48],"speaker":[49],"severity":[51],"independence.":[52],"Additionally,":[53],"inferences":[55],"three":[58],"pre-trained":[59],"SSL":[60,122],"models":[61,123],"used":[63],"as":[64,124,134],"a":[65],"secondary":[66],"baseline.":[67],"Our":[68],"study":[69],"reveals":[70],"that":[71,120],"HuBERT":[72,88],"features":[73],"outperform":[74],"others":[76],"on":[77,94],"TORGO":[79,112],"database,":[80],"while":[81],"Wav2Vec2":[82],"excels":[83],"in":[84,89],"low-severity":[85],"cases":[86,93],"medium":[90],"to":[91],"high-severity":[92],"UAspeech":[96,114],"database.":[97],"We":[98],"observed":[99],"absolute":[100],"improvements":[101],"34%":[103],"28.6%":[105],"over":[106],"zero-shot":[107],"decoding":[108],"results":[109],"databases,":[115],"respectively.":[116],"These":[117],"findings":[118],"suggest":[119],"feature":[125],"extractors":[126],"is":[127],"more":[128],"effective":[129],"than":[130],"them":[132],"directly":[133]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-27T08:22:11.395708","created_date":"2025-10-10T00:00:00"}