{"id":"https://openalex.org/W4408352300","doi":"https://doi.org/10.1109/icassp49660.2025.10889046","title":"Dysarthric Speech Conformer: Adaptation for Sequence-to-Sequence Dysarthric Speech Recognition","display_name":"Dysarthric Speech Conformer: Adaptation for Sequence-to-Sequence Dysarthric Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352300","doi":"https://doi.org/10.1109/icassp49660.2025.10889046"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5030326194","display_name":"Qianli Wang","orcid":"https://orcid.org/0000-0001-5834-2087"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Qianli Wang","raw_affiliation_strings":["University of Auckland,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056555652","display_name":"Zihan Zhong","orcid":"https://orcid.org/0009-0009-9809-4589"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Zihan Zhong","raw_affiliation_strings":["University of Auckland,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033363489","display_name":"Satwinder Singh","orcid":"https://orcid.org/0000-0002-2555-075X"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Satwinder Singh","raw_affiliation_strings":["University of Auckland,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056256178","display_name":"Clarion Mendes","orcid":"https://orcid.org/0000-0003-4207-748X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clarion Mendes","raw_affiliation_strings":["University of Illinois,Champaign,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois,Champaign,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111477492","display_name":"Mark Hasegawa-Johnson","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois,Champaign,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois,Champaign,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043619920","display_name":"Waleed H. Abdulla","orcid":"https://orcid.org/0000-0002-1812-4285"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Waleed Abdulla","raw_affiliation_strings":["University of Auckland,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043278328","display_name":"Seyed Reza Shahamiri","orcid":"https://orcid.org/0000-0003-1543-5931"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Seyed Reza Shahamiri","raw_affiliation_strings":["University of Auckland,Auckland,New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9914000034332275,"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":0.9914000034332275,"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":0.9866999983787537,"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":0.9531000256538391,"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":0.7858454585075378},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.708875298500061},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6015677452087402},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.46534430980682373},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.4316829442977905},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1680775284767151},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.15353083610534668},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0700678825378418},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.05536431074142456},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.05232018232345581}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7858454585075378},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.708875298500061},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6015677452087402},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.46534430980682373},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.4316829442977905},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1680775284767151},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.15353083610534668},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0700678825378418},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.05536431074142456},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.05232018232345581},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":32,"referenced_works":["https://openalex.org/W38194800","https://openalex.org/W97005208","https://openalex.org/W180052447","https://openalex.org/W1494198834","https://openalex.org/W2012360718","https://openalex.org/W2015441235","https://openalex.org/W2018363392","https://openalex.org/W2165698076","https://openalex.org/W2407080277","https://openalex.org/W2766219058","https://openalex.org/W2888807255","https://openalex.org/W2889074736","https://openalex.org/W2936774411","https://openalex.org/W2964525587","https://openalex.org/W3014690389","https://openalex.org/W3025165719","https://openalex.org/W3086105743","https://openalex.org/W3094861110","https://openalex.org/W3097829404","https://openalex.org/W3097945073","https://openalex.org/W3157063407","https://openalex.org/W3167533889","https://openalex.org/W3194248215","https://openalex.org/W3207244775","https://openalex.org/W4223646484","https://openalex.org/W4224138147","https://openalex.org/W4386025707","https://openalex.org/W4387672817","https://openalex.org/W4400275735","https://openalex.org/W6682132143","https://openalex.org/W6739901393","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2331173358","https://openalex.org/W2969484279","https://openalex.org/W3160456149","https://openalex.org/W2168872498","https://openalex.org/W4400873482","https://openalex.org/W2329762060","https://openalex.org/W2517018229"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"holds":[4],"immense":[5],"potential":[6],"to":[7,32,38,70,72],"provide":[8],"an":[9,90],"effective":[10],"interface":[11],"for":[12,20,76,83],"assistive":[13],"technologies,":[14],"but":[15],"its":[16],"performance":[17,80,123],"remains":[18],"unsatisfactory":[19],"people":[21],"with":[22],"speech":[23,36,45,69],"impairments":[24],"such":[25],"as":[26],"dysarthria.":[27],"Existing":[28],"ASR":[29,74,79],"systems":[30],"struggle":[31],"accurately":[33],"recognize":[34],"dysarthric":[35,44,50,77],"due":[37],"the":[39,47,63,98,104,128,131,136],"significant":[40],"speaker":[41],"variability":[42],"in":[43,135],"and":[46,86,101],"scarcity":[48],"of":[49,95],"datasets.":[51],"In":[52],"this":[53],"study,":[54],"we":[55],"propose":[56],"a":[57],"two-phase":[58],"adaptation":[59,129],"pipeline":[60],"based":[61],"on":[62,97,103,130],"Conformer":[64],"architecture":[65],"that":[66,121],"leverages":[67],"typical":[68],"transfer":[71],"individualized":[73],"models":[75],"speakers.":[78],"is":[81,124],"evaluated":[82],"isolated":[84],"words":[85],"continuous":[87],"sentences,":[88],"yielding":[89],"average":[91],"Word":[92],"Error":[93],"Rate":[94],"21.5%":[96],"UASpeech":[99],"dataset":[100],"12.7%":[102],"TORGO":[105],"dataset.":[106],"Selectively":[107],"freezing":[108,117],"decoder":[109],"layers":[110],"was":[111],"more":[112],"often":[113],"successful":[114],"than":[115],"selectively":[116],"encoder":[118],"layers,":[119],"suggesting":[120],"optimal":[122],"achieved":[125],"by":[126],"focusing":[127],"acoustic":[132],"information":[133],"contained":[134],"encoder.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
