{"id":"https://openalex.org/W4392909075","doi":"https://doi.org/10.1109/icassp48485.2024.10447702","title":"Enhancing Pre-Trained ASR System Fine-Tuning for Dysarthric Speech Recognition Using Adversarial Data Augmentation","display_name":"Enhancing Pre-Trained ASR System Fine-Tuning for Dysarthric Speech Recognition Using Adversarial Data Augmentation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909075","doi":"https://doi.org/10.1109/icassp48485.2024.10447702"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5000600118","display_name":"Huimeng Wang","orcid":"https://orcid.org/0000-0002-4280-503X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Huimeng Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"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":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zengrui Jin","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, 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":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Mengzhe Geng","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","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":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shujie Hu","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042515126","display_name":"Guinan Li","orcid":"https://orcid.org/0000-0002-2206-0237"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Guinan Li","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407750","display_name":"Tianzi Wang","orcid":"https://orcid.org/0009-0005-5823-3039"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tianzi Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063907750","display_name":"Haoning Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haoning Xu","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","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":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12311","last_page":"12315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.7613565921783447},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7410969138145447},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6115881204605103},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5899085402488708},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5485417246818542},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.463714599609375},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.4144185483455658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3758825361728668},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.07906696200370789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613565921783447},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7410969138145447},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6115881204605103},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5899085402488708},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5485417246818542},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.463714599609375},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.4144185483455658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3758825361728668},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.07906696200370789},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":46,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W1932968309","https://openalex.org/W1989674786","https://openalex.org/W2168510624","https://openalex.org/W2396944218","https://openalex.org/W2407080277","https://openalex.org/W2798571323","https://openalex.org/W2936861580","https://openalex.org/W2962780374","https://openalex.org/W3014690389","https://openalex.org/W3036601975","https://openalex.org/W3095123370","https://openalex.org/W3161873458","https://openalex.org/W3163725792","https://openalex.org/W3174329270","https://openalex.org/W3196511136","https://openalex.org/W3197642003","https://openalex.org/W3198218550","https://openalex.org/W3198429080","https://openalex.org/W3198806843","https://openalex.org/W3202370288","https://openalex.org/W3207399576","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221153068","https://openalex.org/W4221162789","https://openalex.org/W4226074601","https://openalex.org/W4283461667","https://openalex.org/W4296068414","https://openalex.org/W4297030419","https://openalex.org/W4297841331","https://openalex.org/W4297841875","https://openalex.org/W4323030227","https://openalex.org/W4360993686","https://openalex.org/W4362696744","https://openalex.org/W4372263660","https://openalex.org/W4372341972","https://openalex.org/W4385822286","https://openalex.org/W4385822655","https://openalex.org/W4385822966","https://openalex.org/W4385823120","https://openalex.org/W4387682382","https://openalex.org/W6603616073","https://openalex.org/W6780218876","https://openalex.org/W6810168380","https://openalex.org/W6850409715"],"related_works":["https://openalex.org/W2084983866","https://openalex.org/W3012459429","https://openalex.org/W3015238377","https://openalex.org/W2027206961","https://openalex.org/W2318301054","https://openalex.org/W2754882168","https://openalex.org/W2091380405","https://openalex.org/W2299746430","https://openalex.org/W4312547701","https://openalex.org/W2890040947"],"abstract_inverted_index":{"Automatic":[0],"recognition":[1],"of":[2,55,64,78,89,168,184],"dysarthric":[3,35,70,100,170],"speech":[4,36,92],"remains":[5],"a":[6],"highly":[7],"challenging":[8],"task":[9],"to":[10,33,42,60,69,153],"date.":[11],"Neuro-motor":[12],"conditions":[13],"and":[14,128,135,155,159],"co-occurring":[15],"physical":[16],"disabilities":[17],"create":[18],"difficulty":[19],"in":[20],"large-scale":[21],"data":[22,57,108,122,133,140],"collection":[23],"for":[24],"ASR":[25,31,66],"system":[26,178],"development.":[27],"Adapting":[28],"SSL":[29],"pre-trained":[30,65],"models":[32,130],"limited":[34],"via":[37],"data-intensive":[38],"parameter":[39],"fine-tuning":[40,68],"leads":[41],"poor":[43],"generalization.":[44],"To":[45],"this":[46,48],"end,":[47],"paper":[49],"presents":[50],"an":[51],"extensive":[52],"comparative":[53],"study":[54],"various":[56],"augmentation":[58,109,123,134],"approaches":[59],"improve":[61],"the":[62,117,164,176,180],"robustness":[63],"model":[67],"speech.":[71],"These":[72],"include:":[73],"a)":[74],"conventional":[75],"speaker-independent":[76],"perturbation":[77,88,137],"impaired":[79],"speech;":[80,101],"b)":[81],"speaker-dependent":[82],"speed":[83,136],"perturbation,":[84],"or":[85],"GAN-based":[86,106,121],"adversarial":[87,107],"normal,":[90],"control":[91],"based":[93],"on":[94,111,116,163,187,191],"their":[95],"time":[96],"alignment":[97],"against":[98],"parallel":[99],"c)":[102],"novel":[103],"Spectral":[104],"basis":[105],"operating":[110,142],"non-parallel":[112],"data.":[113],"Experiments":[114],"conducted":[115],"UASpeech":[118,165],"corpus":[119],"suggest":[120],"consistently":[124],"outperforms":[125],"fine-tuned":[126],"Wav2vec2.0":[127],"HuBERT":[129],"using":[131],"no":[132],"across":[138],"different":[139],"expansion":[141],"points":[143],"by":[144],"statistically":[145],"significant":[146],"word":[147],"error":[148],"rate":[149],"(WER)":[150],"reductions":[151],"up":[152],"2.01%":[154],"0.96%":[156],"absolute":[157],"(9.03%":[158],"4.63%":[160],"relative)":[161],"respectively":[162],"test":[166],"set":[167],"16":[169],"speakers.":[171],"After":[172],"cross-system":[173],"outputs":[174],"rescoring,":[175],"best":[177],"produced":[179],"lowest":[181],"published":[182],"WER":[183],"16.53%":[185],"(46.47%":[186],"very":[188],"low":[189],"intelligibility)":[190],"UASpeech.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
