{"id":"https://openalex.org/W4387042351","doi":"https://doi.org/10.1109/taslp.2023.3319276","title":"CFDRN: A Cognition-Inspired Feature Decomposition and Recombination Network for Dysarthric Speech Recognition","display_name":"CFDRN: A Cognition-Inspired Feature Decomposition and Recombination Network for Dysarthric Speech Recognition","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387042351","doi":"https://doi.org/10.1109/taslp.2023.3319276"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3319276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3319276","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5003755490","display_name":"Yuqin Lin","orcid":"https://orcid.org/0000-0003-4842-9263"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuqin Lin","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computingand Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-4842-9263","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computingand Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computingand Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","Huiyan Technology (Tianjin) Co.,Ltd, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8094-6861","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computingand Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Huiyan Technology (Tianjin) Co.,Ltd, Tianjin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanbing Yang","orcid":"https://orcid.org/0009-0003-3425-2599"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbing Yang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computingand Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0003-3425-2599","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computingand Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China","Tianjin Key Laboratory of Cognitive Computingand Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-9237-4821","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computingand Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003755490"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":1.3633,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8494022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"3824","last_page":"3836"},"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":0.9997000098228455,"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":0.9994999766349792,"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/dysarthria","display_name":"Dysarthria","score":0.6887184977531433},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6317571401596069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6026920080184937},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5141785144805908},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5092307329177856},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4867875277996063},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.43998515605926514},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43330058455467224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40874478220939636},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32349592447280884},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14129206538200378},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0719853937625885}],"concepts":[{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.6887184977531433},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6317571401596069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6026920080184937},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5141785144805908},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5092307329177856},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4867875277996063},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.43998515605926514},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43330058455467224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40874478220939636},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32349592447280884},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14129206538200378},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0719853937625885},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3319276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3319276","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G7732325329","display_name":null,"funder_award_id":"62176182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W97005208","https://openalex.org/W253551670","https://openalex.org/W1494198834","https://openalex.org/W1588531540","https://openalex.org/W1985969995","https://openalex.org/W1987435081","https://openalex.org/W2014498736","https://openalex.org/W2018363392","https://openalex.org/W2028824762","https://openalex.org/W2033698660","https://openalex.org/W2053741679","https://openalex.org/W2056486423","https://openalex.org/W2100509922","https://openalex.org/W2109023847","https://openalex.org/W2109848220","https://openalex.org/W2118225053","https://openalex.org/W2134315375","https://openalex.org/W2140686411","https://openalex.org/W2171360373","https://openalex.org/W2407080277","https://openalex.org/W2423557781","https://openalex.org/W2735944051","https://openalex.org/W2744771704","https://openalex.org/W2790414498","https://openalex.org/W2798571323","https://openalex.org/W2888807255","https://openalex.org/W2892009249","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2936861580","https://openalex.org/W2938757327","https://openalex.org/W2972970915","https://openalex.org/W2973049979","https://openalex.org/W2974665356","https://openalex.org/W2980177172","https://openalex.org/W3014690389","https://openalex.org/W3015693260","https://openalex.org/W3015721889","https://openalex.org/W3095123370","https://openalex.org/W3097866346","https://openalex.org/W3120067823","https://openalex.org/W3161716720","https://openalex.org/W3170201991","https://openalex.org/W3174329270","https://openalex.org/W3176485460","https://openalex.org/W3196468567","https://openalex.org/W3197912841","https://openalex.org/W3198702383","https://openalex.org/W3201225328","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4223646484","https://openalex.org/W4223932119","https://openalex.org/W4224918597","https://openalex.org/W4224931267","https://openalex.org/W4224932111","https://openalex.org/W4283073456","https://openalex.org/W4293793697","https://openalex.org/W4296068414","https://openalex.org/W4297030419","https://openalex.org/W6607196876","https://openalex.org/W6631190155","https://openalex.org/W6753111814","https://openalex.org/W6759579507","https://openalex.org/W6775988622","https://openalex.org/W6780218876","https://openalex.org/W6810007534","https://openalex.org/W6838701581"],"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":{"As":[0],"an":[1,138],"essential":[2],"technology":[3],"in":[4,34,48,61,74,80,151],"human\u2013computer":[5],"interactions,":[6],"automatic":[7],"speech":[8,21,60,75,82,87,173],"recognition":[9],"(ASR)":[10],"ensures":[11],"a":[12,29,92],"convenient":[13],"life":[14],"for":[15,100],"healthy":[16],"people;":[17],"however,":[18],"people":[19],"with":[20,214],"disorders,":[22],"who":[23],"truly":[24],"need":[25],"support":[26],"from":[27,171],"such":[28],"technology,":[30],"have":[31],"experienced":[32],"difficulties":[33],"the":[35,45,62,104,131,159,162,166,180,186,208,211,215,238],"use":[36],"of":[37,44,59,67,161,179],"ASR.":[38,102,153],"Disordered":[39],"ASR":[40,253],"is":[41,169],"challenging":[42],"because":[43],"large":[46],"variabilities":[47],"disordered":[49,81,175],"speech.":[50,176],"Humans":[51],"tend":[52],"to":[53,113,128,146,158,174,207],"separately":[54],"process":[55],"different":[56],"spectro-temporal":[57],"features":[58,115],"left":[63],"and":[64,96,107,118,165,190,203,226,240],"right":[65],"hemispheres":[66],"their":[68],"brain,":[69],"showing":[70],"significantly":[71],"better":[72],"ability":[73],"perception":[76],"than":[77],"machines,":[78],"especially":[79],"perception.":[83],"Inspired":[84],"by":[85],"human":[86],"processing,":[88],"this":[89,135,245],"paper":[90],"proposes":[91],"cognition-inspired":[93],"feature":[94],"decomposition":[95],"recombination":[97],"network":[98],"(CFDRN)":[99],"dysarthric":[101,152,252],"In":[103],"CFDRN,":[105],"slow-":[106],"rapid-varying":[108],"temporal":[109],"processors":[110],"are":[111],"designed":[112],"decompose":[114],"into":[116],"stable":[117],"changeable":[119],"features,":[120],"respectively.":[121,243],"A":[122],"gated":[123],"fusion":[124],"module":[125],"was":[126,183],"developed":[127],"selectively":[129],"recombine":[130],"decomposed":[132],"features.":[133],"Moreover,":[134],"study":[136,246],"utilised":[137],"adaptation":[139],"approach":[140],"based":[141],"on":[142,185,237],"unsupervised":[143,197],"pre-training":[144,198,217],"techniques":[145,218],"alleviate":[147],"data":[148],"scarcity":[149],"issues":[150],"The":[154,177],"CFDRNs":[155],"were":[156],"added":[157],"layers":[160],"pre-trained":[163],"model,":[164],"entire":[167],"model":[168],"adapted":[170],"normal":[172],"effectiveness":[178],"proposed":[181,212],"method":[182],"validated":[184],"widely":[187],"used":[188],"TORGO":[189,239],"UASpeech":[191,241],"dysarthria":[192],"datasets":[193],"under":[194],"three":[195,216],"popular":[196],"techniques,":[199],"wav2vec":[200],"2.0,":[201],"HuBERT,":[202],"data2vec.":[204],"When":[205],"compared":[206],"baseline":[209],"methods,":[210],"CFDRN":[213],"achieved":[219],"13.73%":[220],"<inline-formula":[221,228],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[222,229],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[223,230],"notation=\"LaTeX\">$\\sim$</tex-math></inline-formula>":[224,231],"16.23%":[225],"4.50%":[227],"13.20%":[232],"word":[233],"error":[234],"rate":[235],"reductions":[236],"datasets,":[242],"Furthermore,":[244],"clarified":[247],"several":[248],"major":[249],"factors":[250],"affecting":[251],"performance.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}