{"id":"https://openalex.org/W4297030419","doi":"https://doi.org/10.1109/taslp.2022.3205766","title":"Acoustic Modelling From Raw Source and Filter Components for Dysarthric Speech Recognition","display_name":"Acoustic Modelling From Raw Source and Filter Components for Dysarthric Speech Recognition","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4297030419","doi":"https://doi.org/10.1109/taslp.2022.3205766"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3205766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3205766","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":true,"oa_status":"green","oa_url":"https://kclpure.kcl.ac.uk/ws/files/179852223/Source_Filter_Journal_final_2.pdf","any_repository_has_fulltext":true},"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/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"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":"Zhengjun Yue","raw_affiliation_strings":["King's College London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-1101-549X","affiliations":[{"raw_affiliation_string":"King's College London, London, U.K","institution_ids":["https://openalex.org/I4210119896","https://openalex.org/I183935753"]}]},{"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/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"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, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8761-021X","affiliations":[{"raw_affiliation_string":"King's College London, London, U.K","institution_ids":["https://openalex.org/I4210119896","https://openalex.org/I183935753"]}]},{"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, University of Sheffield, Sheffield, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, University of Sheffield, Sheffield, U.K","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","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, University of Sheffield, Sheffield, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, University of Sheffield, Sheffield, U.K","institution_ids":["https://openalex.org/I91136226"]}]},{"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/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"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, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-5128-5099","affiliations":[{"raw_affiliation_string":"King's College London, London, U.K","institution_ids":["https://openalex.org/I4210119896","https://openalex.org/I183935753"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9135,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92080453,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"2968","last_page":"2980"},"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.770922064781189},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7198058366775513},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5965614318847656},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5092257261276245},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.4600403904914856},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4539669454097748},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3796512484550476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3699623942375183},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3228505253791809}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770922064781189},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7198058366775513},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5965614318847656},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5092257261276245},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.4600403904914856},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4539669454097748},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3796512484550476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3699623942375183},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3228505253791809},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2022.3205766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3205766","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"},{"id":"pmh:oai:eprints.whiterose.ac.uk:192463","is_oa":false,"landing_page_url":"https://orcid.org/0000-0003-3028-5062>","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":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/f269301b-2efb-4ad4-83f0-7f2b98076bdf","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/f269301b-2efb-4ad4-83f0-7f2b98076bdf","pdf_url":"https://kclpure.kcl.ac.uk/ws/files/179852223/Source_Filter_Journal_final_2.pdf","source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yue, Z, Loweimi, E, Christensen, H, Barker, J & Cvetkovic, Z 2022, 'Acoustic Modelling from Raw Source and Filter Components for Dysarthric Speech Recognition', IEEE/ACM Transactions on Audio, Speech, and Language Processing , vol. 30, pp. 2968-2980. https://doi.org/10.1109/TASLP.2022.3205766","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:repository@napier.ac.uk:3585801","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3585801","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":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/f269301b-2efb-4ad4-83f0-7f2b98076bdf","is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/f269301b-2efb-4ad4-83f0-7f2b98076bdf","pdf_url":"https://kclpure.kcl.ac.uk/ws/files/179852223/Source_Filter_Journal_final_2.pdf","source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yue, Z, Loweimi, E, Christensen, H, Barker, J & Cvetkovic, Z 2022, 'Acoustic Modelling from Raw Source and Filter Components for Dysarthric Speech Recognition', IEEE/ACM Transactions on Audio, Speech, and Language Processing , vol. 30, pp. 2968-2980. https://doi.org/10.1109/TASLP.2022.3205766","raw_type":"info:eu-repo/semantics/publishedVersion"},"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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297030419.pdf","grobid_xml":"https://content.openalex.org/works/W4297030419.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W1494198834","https://openalex.org/W1586176709","https://openalex.org/W1972928932","https://openalex.org/W2005358137","https://openalex.org/W2005708641","https://openalex.org/W2018363392","https://openalex.org/W2037453437","https://openalex.org/W2076895998","https://openalex.org/W2079623482","https://openalex.org/W2085628288","https://openalex.org/W2089468765","https://openalex.org/W2095705004","https://openalex.org/W2109848220","https://openalex.org/W2127141656","https://openalex.org/W2148154194","https://openalex.org/W2150769028","https://openalex.org/W2151936436","https://openalex.org/W2168510624","https://openalex.org/W2187089797","https://openalex.org/W2217954322","https://openalex.org/W2396944218","https://openalex.org/W2401277329","https://openalex.org/W2547793174","https://openalex.org/W2792759062","https://openalex.org/W2794209590","https://openalex.org/W2798405286","https://openalex.org/W2798571323","https://openalex.org/W2888807255","https://openalex.org/W2889469831","https://openalex.org/W2936861580","https://openalex.org/W2945743426","https://openalex.org/W2964227577","https://openalex.org/W3014344307","https://openalex.org/W3014690389","https://openalex.org/W3015210890","https://openalex.org/W3015537910","https://openalex.org/W3094114204","https://openalex.org/W3094861110","https://openalex.org/W3095123370","https://openalex.org/W3099550332","https://openalex.org/W3104896896","https://openalex.org/W3134043075","https://openalex.org/W3163845842","https://openalex.org/W3174329270","https://openalex.org/W3197553328","https://openalex.org/W3198806843","https://openalex.org/W4224918597","https://openalex.org/W4224932111","https://openalex.org/W4232318280","https://openalex.org/W4294646197","https://openalex.org/W4298442010","https://openalex.org/W6607196876","https://openalex.org/W6631362777","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6736057607","https://openalex.org/W6750254146","https://openalex.org/W6775988622","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W3162157266","https://openalex.org/W2162084437","https://openalex.org/W2102353451","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2400533375","https://openalex.org/W2097143083"],"abstract_inverted_index":{"Acoustic":[0],"modelling":[1],"for":[2,50,64,221],"automatic":[3],"dysarthric":[4,24,115,203,222],"speech":[5,25,116,204],"recognition":[6],"(ADSR)":[7],"is":[8,14],"a":[9,15,82,111,127,211],"challenging":[10],"task.":[11],"Data":[12],"deficiency":[13],"major":[16],"problem":[17],"and":[18,23,47,60,69,92,95,105,121,124,138,175,190,201,218],"substantial":[19],"differences":[20],"between":[21],"typical":[22],"complicate":[26],"the":[27,40,45,89,134,140,151,157,162,179,187,197,206],"transfer":[28],"learning.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,132],"aim":[34],"at":[35,72],"building":[36],"acoustic":[37],"models":[38,55],"using":[39],"raw":[41,173],"magnitude":[42],"spectra":[43],"of":[44,57,76,114,142,186,214],"source":[46],"filter":[48],"components":[49,94],"ADSR.":[51],"The":[52],"proposed":[53,163,207],"multi-stream":[54,83,164],"consist":[56],"convolutional,":[58],"recurrent":[59],"fully-connected":[61],"layers":[62,144],"allowing":[63],"pre-processing":[65],"various":[66,167],"information":[67,86],"streams":[68],"fusing":[70],"them":[71],"an":[73],"optimal":[74],"level":[75],"abstraction.":[77],"We":[78,159],"demonstrate":[79,149],"that":[80,117],"such":[81,101],"processing":[84],"leverages":[85],"encoded":[87],"in":[88,126],"vocal":[90],"tract":[91],"excitation":[93],"leads":[96,109,209],"to":[97,110,148,210,216],"normalising":[98],"nuisance":[99],"factors":[100],"as":[102,182,184],"speaker":[103],"attributes":[104,153],"speaking":[106],"style.":[107],"This":[108],"better":[112],"handling":[113],"exhibits":[118],"large":[119],"inter-":[120],"intra-speaker":[122],"variabilities":[123],"results":[125],"notable":[128],"performance":[129,213],"gain.":[130],"Furthermore,":[131],"analyse":[133],"learned":[135],"convolutional":[136],"filters":[137],"visualise":[139],"outputs":[141],"different":[143],"after":[145],"dimensionality":[146],"reduction":[147],"how":[150],"speaker-related":[152],"are":[154],"normalised":[155],"along":[156],"pipeline.":[158],"also":[160],"compare":[161],"model":[165],"with":[166],"systems":[168],"based":[169],"on":[170],"MFCC,":[171],"FBank,":[172],"waveform":[174],"i-vector,":[176],"and,":[177],"study":[178],"training":[180],"dynamics":[181],"well":[183],"usefulness":[185],"feature":[188],"normalisation":[189],"data":[191],"augmentation":[192],"via":[193],"speed":[194],"perturbation.":[195],"On":[196],"widely":[198],"used":[199],"TORGO":[200],"UASpeech":[202],"corpora,":[205],"approach":[208],"competitive":[212],"up":[215],"35.3%":[217],"30.3%":[219],"WERs":[220],"speech,":[223],"respectively.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}