{"id":"https://openalex.org/W4408355119","doi":"https://doi.org/10.1109/icassp49660.2025.10888412","title":"End-to-end acoustic-articulatory dysarthric speech recognition leveraging large-scale pretrained acoustic features","display_name":"End-to-end acoustic-articulatory dysarthric speech recognition leveraging large-scale pretrained acoustic features","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355119","doi":"https://doi.org/10.1109/icassp49660.2025.10888412"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888412","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/A5053209750","display_name":"Zhengjun Yue","orcid":"https://orcid.org/0000-0002-1101-549X"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zhengjun Yue","raw_affiliation_strings":["Delft University of Technology,Multimedia Computing Group,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Multimedia Computing Group,The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100320635","display_name":"Yuanyuan Zhang","orcid":"https://orcid.org/0000-0001-9738-604X"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yuanyuan Zhang","raw_affiliation_strings":["Delft University of Technology,Multimedia Computing Group,The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Multimedia Computing Group,The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.9872000217437744,"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":0.9872000217437744,"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":0.9815999865531921,"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":0.9574999809265137,"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":0.7603379487991333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7223755717277527},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5628002882003784},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4924553334712982},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.425708532333374},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3520795404911041},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3170716166496277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2676661014556885}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7603379487991333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7223755717277527},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5628002882003784},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4924553334712982},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.425708532333374},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3520795404911041},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3170716166496277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2676661014556885},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888412","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W190072254","https://openalex.org/W1589867908","https://openalex.org/W1932968309","https://openalex.org/W2018363392","https://openalex.org/W2124460610","https://openalex.org/W2148154194","https://openalex.org/W2151936436","https://openalex.org/W2173629880","https://openalex.org/W2401277329","https://openalex.org/W2407080277","https://openalex.org/W2883245269","https://openalex.org/W2962780374","https://openalex.org/W3014344307","https://openalex.org/W3015210890","https://openalex.org/W3094861110","https://openalex.org/W3097777922","https://openalex.org/W3104295320","https://openalex.org/W3157063407","https://openalex.org/W3160719719","https://openalex.org/W3161018648","https://openalex.org/W3174329270","https://openalex.org/W3198429080","https://openalex.org/W3207558756","https://openalex.org/W4221148457","https://openalex.org/W4224932111","https://openalex.org/W4297030419","https://openalex.org/W4297841875","https://openalex.org/W4323315382","https://openalex.org/W4391021580","https://openalex.org/W4401609418","https://openalex.org/W6607196876","https://openalex.org/W6631362777","https://openalex.org/W6737496325","https://openalex.org/W6775988622","https://openalex.org/W6780218876","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4404782863","https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W4383605217","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W2533508831","https://openalex.org/W1599055764","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Automatic":[0],"dysarthric":[1,23,105,113],"speech":[2,12,24],"recognition":[3],"(ADSR)":[4],"remains":[5],"challenging":[6],"due":[7],"to":[8],"the":[9,19,29,58,76,87,97],"irregularities":[10],"in":[11],"caused":[13],"by":[14],"motor":[15],"control":[16],"impairments":[17],"and":[18,44,53,71],"limited":[20],"availability":[21],"of":[22,31,118],"data.":[25],"This":[26],"paper":[27],"explores":[28],"integration":[30],"articulatory":[32,94],"features,":[33],"captured":[34],"using":[35,86],"Electromagnetic":[36],"Articulography":[37],"(EMA),":[38],"with":[39,93,107],"both":[40],"conventional":[41],"acoustic":[42],"features":[43,90,95],"those":[45],"extracted":[46],"from":[47],"large-scale":[48],"pretrained":[49],"models":[50,68],"including":[51],"Whisper":[52,60,89],"XLSR-53":[54],"as":[55,57],"well":[56],"fine-tuned":[59,88],"model.":[61],"We":[62],"propose":[63],"end-to-end":[64],"(E2E)":[65],"Conformer-based":[66],"acoustic-articulatory":[67],"for":[69,111],"ADSR":[70],"compare":[72],"their":[73],"performance":[74],"against":[75],"corresponding":[77],"hybrid":[78],"TDNNF":[79],"models.":[80],"The":[81],"experimental":[82],"results":[83],"show":[84],"that":[85],"(Whisper-FT)":[91],"fused":[92],"achieves":[96],"lowest":[98],"(10.5%)":[99],"word":[100],"error":[101],"rate":[102],"(WER)":[103],"on":[104],"speech,":[106,114],"particularly":[108],"significant":[109],"improvements":[110],"severely":[112],"reaching":[115],"a":[116],"WER":[117],"20.8%.":[119]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}