{"id":"https://openalex.org/W4372263660","doi":"https://doi.org/10.1109/icassp49357.2023.10097275","title":"Exploring Self-Supervised Pre-Trained ASR Models for Dysarthric and Elderly Speech Recognition","display_name":"Exploring Self-Supervised Pre-Trained ASR Models for Dysarthric and Elderly Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372263660","doi":"https://doi.org/10.1109/icassp49357.2023.10097275"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097275","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/A5026334377","display_name":"Shujie Hu","orcid":"https://orcid.org/0000-0002-8475-4912"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shujie Hu","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035857878","display_name":"Xurong Xie","orcid":"https://orcid.org/0000-0002-6714-6296"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xurong Xie","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Software,China","Institute of Software, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Software,China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075023049","display_name":"Zengrui Jin","orcid":"https://orcid.org/0000-0002-2637-7880"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengrui Jin","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003895235","display_name":"Mengzhe Geng","orcid":"https://orcid.org/0000-0002-7886-439X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengzhe Geng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364952","display_name":"Yi Wang","orcid":"https://orcid.org/0000-0002-4174-8790"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065896539","display_name":"Mingyu Cui","orcid":"https://orcid.org/0000-0001-9781-9407"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Cui","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106406454","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-8874-4167"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5026334377"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":4.8346,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.96035346,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9994000196456909,"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":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7599056959152222},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6748267412185669},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5583467483520508},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5425221920013428},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.529462993144989},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4654439687728882},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45999017357826233},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4534095525741577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44892263412475586},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4168274998664856},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4127961993217468},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0957949161529541}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7599056959152222},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6748267412185669},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5583467483520508},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5425221920013428},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.529462993144989},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4654439687728882},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45999017357826233},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4534095525741577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44892263412475586},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4168274998664856},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4127961993217468},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0957949161529541},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097275","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/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W2014886338","https://openalex.org/W2074037951","https://openalex.org/W2127141656","https://openalex.org/W2160650576","https://openalex.org/W2402146185","https://openalex.org/W2547875792","https://openalex.org/W2886342482","https://openalex.org/W2888789389","https://openalex.org/W3014690389","https://openalex.org/W3015693260","https://openalex.org/W3036601975","https://openalex.org/W3095123370","https://openalex.org/W3097777922","https://openalex.org/W3134043075","https://openalex.org/W3143787022","https://openalex.org/W3161873458","https://openalex.org/W3174329270","https://openalex.org/W3197642003","https://openalex.org/W3197712601","https://openalex.org/W3197912841","https://openalex.org/W3198429080","https://openalex.org/W3198702383","https://openalex.org/W3198771897","https://openalex.org/W3202370288","https://openalex.org/W3205665014","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4210366248","https://openalex.org/W4221162789","https://openalex.org/W4226074601","https://openalex.org/W4254312214","https://openalex.org/W4280574981","https://openalex.org/W4283461667","https://openalex.org/W4283717314","https://openalex.org/W4297030419","https://openalex.org/W4297841331","https://openalex.org/W4297841798","https://openalex.org/W4297841875","https://openalex.org/W4385822856","https://openalex.org/W6684102179","https://openalex.org/W6729448088","https://openalex.org/W6754311675","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6838835331","https://openalex.org/W6839741749"],"related_works":["https://openalex.org/W2084983866","https://openalex.org/W3012459429","https://openalex.org/W2027206961","https://openalex.org/W3015238377","https://openalex.org/W2091380405","https://openalex.org/W4312547701","https://openalex.org/W2081214229","https://openalex.org/W2890040947","https://openalex.org/W3022666696","https://openalex.org/W2909404091"],"abstract_inverted_index":{"Automatic":[0],"recognition":[1,122],"of":[2,30,71,158,176,196],"disordered":[3],"and":[4,43,49,61,81,86,119,130,138,160,164,187,200],"elderly":[5,50,120,133],"speech":[6,51,65,121,134],"remains":[7],"a":[8,28],"highly":[9],"challenging":[10],"task":[11],"to":[12,15,32,95,115],"date":[13],"due":[14],"the":[16,91,127,149,168,192,201],"difficulty":[17],"in":[18,22,111],"collecting":[19],"such":[20],"data":[21],"large":[23],"quantities.":[24],"This":[25],"paper":[26],"explores":[27],"series":[29],"approaches":[31],"integrate":[33],"domain":[34,62,99,105,143],"adapted":[35,63,100,106,144],"Self-Supervised":[36],"Learning":[37],"(SSL)":[38],"pre-trained":[39],"models":[40,146,152],"into":[41],"TDNN":[42,72,137],"Conformer":[44,139],"ASR":[45,140],"systems":[46,73,141],"for":[47],"dysarthric":[48,118,129,198],"recognition:":[52],"a)":[53],"input":[54],"feature":[55],"fusion":[56],"between":[57],"standard":[58,77],"acoustic":[59,78],"frontends":[60],"wav2vec2.0":[64,84,101,107,145,151],"representations;":[66],"b)":[67],"frame-level":[68],"joint":[69],"decoding":[70,89],"separately":[74],"trained":[75],"using":[76,98],"features":[79],"alone":[80],"with":[82],"additional":[83],"features;":[85],"c)":[87],"multi-pass":[88],"involving":[90],"TDNN/Conformer":[92],"system":[93],"outputs":[94],"be":[96],"rescored":[97],"models.":[102],"In":[103],"addition,":[104],"representations":[108],"are":[109,189],"utilized":[110],"acoustic-to-articulatory":[112],"(A2A)":[113],"inversion":[114],"construct":[116],"multi-modal":[117],"systems.":[123],"Experiments":[124],"conducted":[125],"on":[126,167,179,184,191],"UASpeech":[128,193],"DementiaBank":[131,202],"Pitt":[132,203],"corpora":[135],"suggest":[136],"integrated":[142],"consistently":[147],"outperform":[148],"standalone":[150],"by":[153],"statistically":[154],"significant":[155],"WER":[156],"reductions":[157],"8.22%":[159],"3.43%":[161],"absolute":[162],"(26.71%":[163],"15.88%":[165],"relative)":[166],"two":[169],"tasks":[170],"respectively.":[171,206],"The":[172],"lowest":[173],"published":[174],"WERs":[175],"22.56%":[177],"(52.53%":[178],"very":[180],"low":[181],"intelligibility,":[182],"39.09%":[183],"unseen":[185],"words)":[186],"18.17%":[188],"obtained":[190],"test":[194,204],"set":[195,205],"16":[197],"speakers,":[199]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}