{"id":"https://openalex.org/W4224932111","doi":"https://doi.org/10.1109/icassp43922.2022.9746855","title":"Multi-Modal Acoustic-Articulatory Feature Fusion For Dysarthric Speech Recognition","display_name":"Multi-Modal Acoustic-Articulatory Feature Fusion For Dysarthric Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224932111","doi":"https://doi.org/10.1109/icassp43922.2022.9746855"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746855","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5053209750","display_name":"Zhengjun Yue","orcid":"https://orcid.org/0000-0002-1101-549X"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhengjun Yue","raw_affiliation_strings":["Speech and Hearing Research Group (SPandH), University of Sheffield,UK","Speech and Hearing Research Group (SPandH), University of Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group (SPandH), University of Sheffield,UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Speech and Hearing Research Group (SPandH), University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042184515","display_name":"Erfan Loweimi","orcid":"https://orcid.org/0000-0002-8761-021X"},"institutions":[{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erfan Loweimi","raw_affiliation_strings":["King’s College London,Department of Engineering,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King’s College London,Department of Engineering,UK","institution_ids":["https://openalex.org/I4210119896"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056805951","display_name":"Zoran Cvetkovi\u0107","orcid":"https://orcid.org/0000-0002-5128-5099"},"institutions":[{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zoran Cvetkovic","raw_affiliation_strings":["King’s College London,Department of Engineering,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King’s College London,Department of Engineering,UK","institution_ids":["https://openalex.org/I4210119896"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045619924","display_name":"Heidi Christensen","orcid":"https://orcid.org/0000-0003-3028-5062"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Heidi Christensen","raw_affiliation_strings":["Speech and Hearing Research Group (SPandH), University of Sheffield,UK","Speech and Hearing Research Group (SPandH), University of Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group (SPandH), University of Sheffield,UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Speech and Hearing Research Group (SPandH), University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074458312","display_name":"Jon Barker","orcid":"https://orcid.org/0000-0002-1684-5660"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jon Barker","raw_affiliation_strings":["Speech and Hearing Research Group (SPandH), University of Sheffield,UK","Speech and Hearing Research Group (SPandH), University of Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group (SPandH), University of Sheffield,UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Speech and Hearing Research Group (SPandH), University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.0177,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.98967298,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7372","last_page":"7376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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/dysarthria","display_name":"Dysarthria","score":0.7770841717720032},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7483799457550049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7433181405067444},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48814257979393005},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.460319459438324},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.42560243606567383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35563063621520996}],"concepts":[{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.7770841717720032},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7483799457550049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433181405067444},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48814257979393005},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.460319459438324},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.42560243606567383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35563063621520996},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746855","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository@napier.ac.uk:3585830","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3585830","pdf_url":null,"source":{"id":"https://openalex.org/S4306402591","display_name":"Edinburgh Napier Research Repository (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3297227137","display_name":null,"funder_award_id":"EP/R012180/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6167047368","display_name":null,"funder_award_id":"EP/R012067/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W178045984","https://openalex.org/W180052447","https://openalex.org/W190072254","https://openalex.org/W900447646","https://openalex.org/W1589867908","https://openalex.org/W1836465849","https://openalex.org/W2005708641","https://openalex.org/W2018363392","https://openalex.org/W2027297142","https://openalex.org/W2084123349","https://openalex.org/W2095705004","https://openalex.org/W2124460610","https://openalex.org/W2151936436","https://openalex.org/W2696259631","https://openalex.org/W2728212668","https://openalex.org/W2794209590","https://openalex.org/W2883245269","https://openalex.org/W2890952074","https://openalex.org/W3013783381","https://openalex.org/W3014344307","https://openalex.org/W3094861110","https://openalex.org/W3104896896","https://openalex.org/W4232318280","https://openalex.org/W6607196876","https://openalex.org/W6635242571","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6754392867","https://openalex.org/W6775988622","https://openalex.org/W6785327963"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Building":[0],"automatic":[1],"speech":[2,38,51,107],"recognition":[3,52],"(ASR)":[4],"systems":[5],"for":[6,49,72,142],"speakers":[7,143],"with":[8,27,57,144],"dysarthria":[9],"is":[10],"a":[11,128],"very":[12],"challenging":[13],"task.":[14],"Although":[15],"multi-modal":[16,46],"ASR":[17],"has":[18,30],"received":[19],"increasing":[20],"attention":[21],"recently,":[22],"incorporating":[23],"real":[24],"articulatory":[25,58,117],"data":[26],"acoustic":[28,47,54,115],"features":[29,55,118],"not":[31],"been":[32],"widely":[33],"explored":[34],"in":[35,96],"the":[36,43,78,87,103,114,120],"dysarthric":[37,50,106],"community.":[39],"This":[40],"paper":[41],"investigates":[42],"effectiveness":[44],"of":[45,65,81,98,125],"modelling":[48],"using":[53,102],"along":[56],"information.":[59],"The":[60],"proposed":[61],"multi-stream":[62],"architectures":[63],"consist":[64],"convolutional,":[66],"recurrent":[67],"and":[68,83,100,116],"fully-connected":[69],"layers":[70],"allowing":[71],"bespoke":[73],"per-stream":[74],"pre-processing,":[75],"fusion":[76,89],"at":[77,119],"optimal":[79,88,123],"level":[80,124],"abstraction":[82,126],"post-processing.":[84],"We":[85],"study":[86],"level/scheme":[90],"as":[91,93],"well":[92],"training":[94],"dynamics":[95],"terms":[97],"cross-entropy":[99],"WER":[101,140],"popular":[104],"TORGO":[105],"database.":[108],"Experimental":[109],"results":[110],"show":[111],"that":[112],"fusing":[113],"empirically":[121],"found":[122],"achieves":[127],"remarkable":[129],"performance":[130],"gain,":[131],"leading":[132],"to":[133,135],"up":[134],"4.6%":[136],"absolute":[137],"(9.6%":[138],"relative)":[139],"reduction":[141],"dysarthria.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}