{"id":"https://openalex.org/W4224918597","doi":"https://doi.org/10.1109/icassp43922.2022.9746553","title":"Raw Source and Filter Modelling for Dysarthric Speech Recognition","display_name":"Raw Source and Filter Modelling for Dysarthric Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224918597","doi":"https://doi.org/10.1109/icassp43922.2022.9746553"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746553","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/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]},{"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":["King’s College London,Department of Engineering,UK","Speech and Hearing Group (SPandH), University of Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King’s College London,Department of Engineering,UK","institution_ids":["https://openalex.org/I4210119896"]},{"raw_affiliation_string":"Speech and Hearing 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"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erfan Loweimi","raw_affiliation_strings":["King’s College London,Department of Engineering,UK","Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King’s College London,Department of Engineering,UK","institution_ids":["https://openalex.org/I4210119896"]},{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5572,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8471243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7377","last_page":"7381"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.7878320217132568},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7719078063964844},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.5261354446411133},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5228836536407471},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4459091126918793},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41092246770858765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3936508595943451},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2841492295265198},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07421964406967163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878320217132568},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7719078063964844},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.5261354446411133},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5228836536407471},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4459091126918793},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41092246770858765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3936508595943451},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2841492295265198},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07421964406967163}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746553","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:eprints.whiterose.ac.uk:192462","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:repository@napier.ac.uk:3585825","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3585825","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W2005708641","https://openalex.org/W2018363392","https://openalex.org/W2076895998","https://openalex.org/W2095705004","https://openalex.org/W2148154194","https://openalex.org/W2217954322","https://openalex.org/W2396944218","https://openalex.org/W2794209590","https://openalex.org/W2888807255","https://openalex.org/W2936861580","https://openalex.org/W2945743426","https://openalex.org/W2964227577","https://openalex.org/W3013783381","https://openalex.org/W3014344307","https://openalex.org/W3014690389","https://openalex.org/W3094861110","https://openalex.org/W3099550332","https://openalex.org/W3104896896","https://openalex.org/W3163845842","https://openalex.org/W3174329270","https://openalex.org/W3197553328","https://openalex.org/W4232318280","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6775988622","https://openalex.org/W6780226713","https://openalex.org/W6785327963"],"related_works":["https://openalex.org/W3162157266","https://openalex.org/W2162084437","https://openalex.org/W3044927199","https://openalex.org/W2102353451","https://openalex.org/W1969107787","https://openalex.org/W2933771351","https://openalex.org/W2038216521","https://openalex.org/W2736574136","https://openalex.org/W2067459736","https://openalex.org/W2105635394"],"abstract_inverted_index":{"Acoustic":[0],"modelling":[1],"for":[2,60,139,163,181],"automatic":[3],"dysarthric":[4,25,109,149,164,182],"speech":[5,26,110,150,165],"recognition":[6],"(ADSR)":[7],"is":[8,14],"a":[9,15,81,112],"challenging":[10],"task.":[11],"Data":[12],"deficiency":[13],"major":[16],"problem":[17],"and":[18,24,45,55,65,73,89,98,115,136,178,183],"substantial":[19],"differences":[20],"between":[21],"the":[22,38,43,62,95,108,120,127,133,140,145,152,168],"typical":[23,184],"complicates":[27],"transfer":[28],"learning.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"build":[34],"acoustic":[35],"models":[36],"using":[37],"raw":[39],"magnitude":[40],"spectra":[41],"of":[42,53,71,107,132],"source":[44],"filter":[46],"components.":[47],"The":[48],"proposed":[49,121,153],"multi-stream":[50,82],"model":[51,92,173],"consists":[52],"convolutional":[54,142],"recurrent":[56],"layers.":[57],"It":[58],"allows":[59],"fusing":[61],"vocal":[63],"tract":[64],"excitation":[66],"components":[67],"at":[68],"different":[69],"levels":[70],"abstraction":[72],"after":[74],"per-stream":[75],"pre-processing.":[76],"We":[77,118],"show":[78],"that":[79],"such":[80],"processing":[83],"leverages":[84],"these":[85],"two":[86],"information":[87],"streams":[88],"helps":[90],"s":[91],"towards":[93],"normalising":[94],"speaker":[96],"attributes":[97],"speaking":[99],"style.":[100],"This":[101],"potentially":[102],"leads":[103],"to":[104,158,176],"better":[105],"handling":[106],"with":[111,123,167],"large":[113],"inter-speaker":[114],"intra-speaker":[116],"variability.":[117],"compare":[119],"system":[122],"various":[124],"features,":[125],"study":[126],"training":[128],"dynamics,":[129],"explore":[130],"usefulness":[131],"data":[134],"augmentation":[135],"provide":[137],"interpretation":[138],"learned":[141],"filters.":[143],"On":[144],"widely":[146],"used":[147],"TORGO":[148],"corpus,":[151],"approach":[154],"results":[155],"in":[156],"up":[157,175],"1.7%":[159],"absolute":[160],"WER":[161,180],"reduction":[162],"compared":[166],"MFCC":[169],"base-line.":[170],"Our":[171],"best":[172],"reaches":[174],"40.6%":[177],"11.8%":[179],"speech,":[185],"respectively.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}