{"id":"https://openalex.org/W4372259808","doi":"https://doi.org/10.1109/icassp49357.2023.10094605","title":"Automatic Severity Classification of Dysarthric Speech by Using Self-Supervised Model with Multi-Task Learning","display_name":"Automatic Severity Classification of Dysarthric Speech by Using Self-Supervised Model with Multi-Task Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259808","doi":"https://doi.org/10.1109/icassp49357.2023.10094605"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5083656628","display_name":"Eun Jung Yeo","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Eun Jung Yeo","raw_affiliation_strings":["Seoul National University,Department of Linguistics,Republic of Korea","Department of Linguistics, Seoul National University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Linguistics,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Linguistics, Seoul National University, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023799668","display_name":"Kwanghee Choi","orcid":"https://orcid.org/0000-0001-5254-1093"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kwanghee Choi","raw_affiliation_strings":["Sogang University,Department of Computer Science and Engineering,Republic of Korea","Department of Computer Science and Engineering, Sogang University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Sogang University,Department of Computer Science and Engineering,Republic of Korea","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417569","display_name":"Sunhee Kim","orcid":"https://orcid.org/0000-0003-1762-6459"},"institutions":[{"id":"https://openalex.org/I158743462","display_name":"Seoul National University of Education","ror":"https://ror.org/01xts9v65","country_code":"KR","type":"education","lineage":["https://openalex.org/I158743462"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunhee Kim","raw_affiliation_strings":["Seoul National University,Department of French Language Education,Republic of Korea","Department of French Language Education, Seoul National University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of French Language Education,Republic of Korea","institution_ids":["https://openalex.org/I158743462"]},{"raw_affiliation_string":"Department of French Language Education, Seoul National University, Republic of Korea","institution_ids":["https://openalex.org/I158743462"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105294860","display_name":"Minhwa Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minhwa Chung","raw_affiliation_strings":["Seoul National University,Department of Linguistics,Republic of Korea","Department of Linguistics, Seoul National University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Linguistics,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Linguistics, Seoul National University, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083656628"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":1.7433,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84406716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9975000023841858,"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/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7044544219970703},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6110925674438477},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6004965901374817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5919167399406433},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5768983960151672},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5330658555030823},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.4944300651550293},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4808381497859955},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4713895916938782},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4682886004447937},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4572479724884033},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.44330763816833496},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33517807722091675},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07202452421188354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7044544219970703},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6110925674438477},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6004965901374817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5919167399406433},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5768983960151672},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5330658555030823},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.4944300651550293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4808381497859955},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4713895916938782},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4682886004447937},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4572479724884033},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.44330763816833496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33517807722091675},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07202452421188354},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2015441235","https://openalex.org/W2055865013","https://openalex.org/W2064610785","https://openalex.org/W2085662862","https://openalex.org/W2251767758","https://openalex.org/W2786672974","https://openalex.org/W2972572915","https://openalex.org/W2973237404","https://openalex.org/W2999959629","https://openalex.org/W3016192394","https://openalex.org/W3036601975","https://openalex.org/W3039208322","https://openalex.org/W3091860345","https://openalex.org/W3160773219","https://openalex.org/W3196511136","https://openalex.org/W3198524283","https://openalex.org/W3213029956","https://openalex.org/W4224315877","https://openalex.org/W4225654587","https://openalex.org/W4226074601","https://openalex.org/W4287509666","https://openalex.org/W4297841747","https://openalex.org/W4297841770","https://openalex.org/W4297841875","https://openalex.org/W4303685860","https://openalex.org/W4312120782","https://openalex.org/W6691237116","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W4385482737","https://openalex.org/W2948333011","https://openalex.org/W4287630354","https://openalex.org/W3097966281","https://openalex.org/W4386619269","https://openalex.org/W2948473094","https://openalex.org/W3164872277","https://openalex.org/W4390437681","https://openalex.org/W4312745891","https://openalex.org/W1942758450"],"abstract_inverted_index":{"Automatic":[0],"assessment":[1,34],"of":[2,105],"dysarthric":[3,37,89],"speech":[4,15,63,90],"is":[5,16,51],"essential":[6],"for":[7,36,54,107],"sustained":[8],"treatments":[9],"and":[10,60,75,83,142],"rehabilitation.":[11],"However,":[12],"obtaining":[13],"atypical":[14],"challenging,":[17],"often":[18],"leading":[19],"to":[20],"data":[21],"scarcity":[22],"issues.":[23],"To":[24],"tackle":[25],"the":[26,40,67,87,96,111,115,133,139],"problem,":[27],"we":[28,70,127],"propose":[29],"a":[30,101],"novel":[31],"automatic":[32,62],"severity":[33,58,134],"method":[35],"speech,":[38],"using":[39],"self-supervised":[41],"model":[42,94,113,116],"in":[43],"conjunction":[44],"with":[45,100],"multi-task":[46,130],"learning.":[47],"Wav2vec":[48],"2.0":[49],"XLS-R":[50],"jointly":[52],"trained":[53,117],"two":[55],"different":[56],"tasks:":[57],"classification":[59,135],"auxiliary":[61],"recognition":[64],"(ASR).":[65],"For":[66],"baseline":[68,98],"experiments,":[69],"employ":[71],"hand-crafted":[72],"acoustic":[73],"features":[74],"machine":[76],"learning":[77,131],"classifiers":[78],"such":[79],"as":[80],"SVM,":[81],"MLP,":[82],"XGBoost.":[84],"Explored":[85],"on":[86],"Korean":[88],"QoLT":[91],"database,":[92],"our":[93],"out-performs":[95],"traditional":[97],"methods,":[99],"relative":[102,123],"percentage":[103,124],"increase":[104],"1.25%":[106],"F1-score.":[108],"In":[109],"addition,":[110],"proposed":[112],"surpasses":[114],"without":[118],"ASR":[119],"head,":[120],"achieving":[121],"10.61%":[122],"improvements.":[125],"Furthermore,":[126],"present":[128],"how":[129],"affects":[132],"performance":[136],"by":[137],"analyzing":[138],"latent":[140],"representations":[141],"regularization":[143],"effect.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}