{"id":"https://openalex.org/W4296068432","doi":"https://doi.org/10.21437/interspeech.2022-163","title":"Dysarthric Speech Recognition From Raw Waveform with Parametric CNNs","display_name":"Dysarthric Speech Recognition From Raw Waveform with Parametric CNNs","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068432","doi":"https://doi.org/10.21437/interspeech.2022-163"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-163","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-163","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengjun Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042184515","display_name":"Erfan Loweimi","orcid":"https://orcid.org/0000-0002-8761-021X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erfan Loweimi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045619924","display_name":"Heidi Christensen","orcid":"https://orcid.org/0000-0003-3028-5062"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heidi Christensen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074458312","display_name":"Jon Barker","orcid":"https://orcid.org/0000-0002-1684-5660"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jon Barker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056805951","display_name":"Zoran Cvetkovi\u0107","orcid":"https://orcid.org/0000-0002-5128-5099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zoran Cvetkovic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.661,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.86148953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9693999886512756,"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":0.9693999886512756,"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":0.9656000137329102,"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":0.9431999921798706,"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/speech-recognition","display_name":"Speech recognition","score":0.7816952466964722},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7191529273986816},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7045705914497375},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6427522301673889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4309538006782532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35014140605926514},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10684484243392944},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08534908294677734}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7816952466964722},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7191529273986816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7045705914497375},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6427522301673889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4309538006782532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35014140605926514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10684484243392944},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08534908294677734},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-163","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-163","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:repository@napier.ac.uk:3585813","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3585813","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2147042348","https://openalex.org/W2033914206","https://openalex.org/W3003836766","https://openalex.org/W2046077695","https://openalex.org/W2163831990","https://openalex.org/W3171304116","https://openalex.org/W4287120475","https://openalex.org/W2912843901","https://openalex.org/W2610284765","https://openalex.org/W2963015453"],"abstract_inverted_index":{"Raw":[0],"waveform":[1,26,45,90,139],"acoustic":[2,46,91,125,180],"modelling":[3,47,92,126,181],"has":[4],"recently":[5],"received":[6],"increasing":[7],"attention.":[8],"Compared":[9],"with":[10,77],"the":[11,24,36,86,101,104,109,118,129,144,150,155,184],"task-blind":[12],"hand-crafted":[13,136],"features":[14],"which":[15],"may":[16],"discard":[17],"useful":[18],"information,":[19],"representations":[20],"directly":[21],"learned":[22,105],"from":[23],"raw":[25,44,89,138],"are":[27],"task-specific":[28],"and":[29,70,107,123,131,137,162,168,175,191,196],"potentially":[30],"include":[31],"all":[32],"task-relevant":[33],"information.":[34],"In":[35,81],"context":[37],"of":[38,88,103,112,120],"automatic":[39],"dysarthric":[40,146,174,195],"speech":[41],"recognition":[42],"(ADSR),":[43],"is":[48],"under-explored":[49],"owing":[50],"to":[51,65,160,166,189],"data":[52,74,121],"scarcity.":[53],"Parametric":[54],"convolutional":[55],"neural":[56],"networks":[57],"(CNNs)":[58],"can":[59],"compensate":[60],"for":[61,97,173,194],"this":[62,82],"problem":[63],"due":[64],"having":[66],"notably":[67],"fewer":[68],"parameters":[69],"requiring":[71],"less":[72],"training":[73,110],"in":[75,187],"comparison":[76],"conventional":[78],"non-parametric":[79,130,156],"CNNs.":[80],"paper,":[83],"we":[84,116],"explore":[85],"usefulness":[87],"using":[93],"various":[94,113],"parametric":[95,132,151],"CNNs":[96,133,152],"ADSR.":[98],"We":[99],"investigate":[100],"properties":[102],"filters":[106],"monitor":[108],"dynamics":[111],"models.":[114],"Furthermore,":[115],"study":[117],"effectiveness":[119],"augmentation":[122],"multi-stream":[124],"through":[127],"combining":[128],"fed":[134],"by":[135],"features.":[140],"Experimental":[141],"results":[142],"on":[143],"TORGO":[145],"database":[147],"show":[148],"that":[149],"significantly":[153],"outperform":[154],"CNNs,":[157],"reaching":[158],"up":[159,188],"36.2%":[161],"12.6%":[163],"WERs":[164,193],"(up":[165],"3.4%":[167],"1.1%":[169],"absolute":[170],"error":[171],"reduction)":[172],"typical":[176,197],"speech,":[177,198],"respectively.":[178,199],"Multi-stream":[179],"further":[182],"improves":[183],"performance":[185],"resulting":[186],"33.2%":[190],"10.3%":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}