{"id":"https://openalex.org/W4224931267","doi":"https://doi.org/10.1109/icassp43922.2022.9746585","title":"Synthesizing Dysarthric Speech Using Multi-Speaker Tts For Dysarthric Speech Recognition","display_name":"Synthesizing Dysarthric Speech Using Multi-Speaker Tts For Dysarthric Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224931267","doi":"https://doi.org/10.1109/icassp43922.2022.9746585"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746585","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":"conference-paper","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/A5064273942","display_name":"Mohammad Soleymanpour","orcid":null},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Soleymanpour","raw_affiliation_strings":["Electrical and Computer Engineering, University of Kentucky,Lexington,KY,USA,40506"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Kentucky,Lexington,KY,USA,40506","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015797517","display_name":"Michael T. Johnson","orcid":"https://orcid.org/0000-0001-5424-4877"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael T. Johnson","raw_affiliation_strings":["Electrical and Computer Engineering, University of Kentucky,Lexington,KY,USA,40506"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Kentucky,Lexington,KY,USA,40506","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046663267","display_name":"Rahim Soleymanpour","orcid":"https://orcid.org/0000-0001-7848-4138"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahim Soleymanpour","raw_affiliation_strings":["University of Connecticut,Department of Biomedical Engineering,Storrs,CT,USA,06269"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut,Department of Biomedical Engineering,Storrs,CT,USA,06269","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054482143","display_name":"Jeffrey Berry","orcid":"https://orcid.org/0000-0001-6947-0666"},"institutions":[{"id":"https://openalex.org/I102461120","display_name":"Marquette University","ror":"https://ror.org/04gr4te78","country_code":"US","type":"education","lineage":["https://openalex.org/I102461120"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Berry","raw_affiliation_strings":["Speech Pathology and Audiology, Marquette University,Milwaukee,WI,USA,53201"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Pathology and Audiology, Marquette University,Milwaukee,WI,USA,53201","institution_ids":["https://openalex.org/I102461120"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7382","last_page":"7386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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":0.9954000115394592,"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":0.8917111158370972},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7981165647506714},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7926177382469177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6547041535377502},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48708227276802063},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4784431755542755},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.47634103894233704},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4305347502231598},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.26774871349334717},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.09364330768585205}],"concepts":[{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.8917111158370972},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7981165647506714},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7926177382469177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6547041535377502},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48708227276802063},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4784431755542755},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.47634103894233704},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4305347502231598},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.26774871349334717},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.09364330768585205},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746585","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2018363392","https://openalex.org/W2140360678","https://openalex.org/W2547793174","https://openalex.org/W2747874407","https://openalex.org/W2766812927","https://openalex.org/W2792759062","https://openalex.org/W2794209590","https://openalex.org/W2898727538","https://openalex.org/W2912937645","https://openalex.org/W2963609956","https://openalex.org/W2964227577","https://openalex.org/W2964243274","https://openalex.org/W3008480565","https://openalex.org/W3015449694","https://openalex.org/W3033411150","https://openalex.org/W3094861110","https://openalex.org/W3097890746","https://openalex.org/W3104896896","https://openalex.org/W3140836199","https://openalex.org/W3161704465","https://openalex.org/W3200199839","https://openalex.org/W6631362777","https://openalex.org/W6736996214","https://openalex.org/W6745697700","https://openalex.org/W6756385397","https://openalex.org/W6778823374","https://openalex.org/W6801165689"],"related_works":["https://openalex.org/W2084983866","https://openalex.org/W3012459429","https://openalex.org/W3015238377","https://openalex.org/W2027206961","https://openalex.org/W2318301054","https://openalex.org/W2754882168","https://openalex.org/W2091380405","https://openalex.org/W2299746430","https://openalex.org/W4312547701","https://openalex.org/W2890040947"],"abstract_inverted_index":{"Dysarthria":[0],"is":[1,40,43],"a":[2,84,114],"motor":[3],"speech":[4,10,17,39,79,122],"disorder":[5],"often":[6],"characterized":[7],"by":[8,144],"reduced":[9],"intelligibility":[11],"through":[12],"slow,":[13],"uncoordinated":[14],"control":[15,103],"of":[16,59,83,126,134,149],"production":[18],"muscles.":[19],"Automatic":[20],"Speech":[21],"recognition":[22],"(ASR)":[23],"systems":[24,55,75],"may":[25],"help":[26],"dysarthric":[27,78,121],"talkers":[28],"communicate":[29],"more":[30],"effectively.":[31],"To":[32],"have":[33],"robust":[34],"dysarthria-specific":[35,85],"ASR,":[36],"sufficient":[37],"training":[38,82],"required,":[41],"which":[42],"not":[44],"readily":[45],"available.":[46],"Recent":[47],"advances":[48],"in":[49],"Text-To-Speech":[50],"(TTS)":[51],"synthesis":[52,61],"multi-speaker":[53,72],"end-to-end":[54,73],"suggest":[56],"the":[57,89,130,132,135,147],"possibility":[58],"using":[60],"for":[62,80],"data":[63],"augmentation.":[64],"In":[65,88],"this":[66],"paper,":[67],"we":[68,92],"aim":[69],"to":[70,76,101,129],"improve":[71],"TTS":[74],"synthesize":[77],"improved":[81],"DNN-HMM":[86,115],"ASR.":[87],"synthesized":[90],"speech,":[91],"add":[93],"dysarthria":[94],"severity":[95,136],"level":[96,137],"and":[97,109,138],"pause":[98,139],"insertion":[99,140],"mechanisms":[100],"other":[102],"parameters":[104],"such":[105],"as":[106],"pitch,":[107],"energy,":[108],"duration.":[110],"Results":[111],"show":[112],"that":[113],"model":[116],"trained":[117],"on":[118],"additional":[119],"synthetic":[120],"achieves":[123],"WER":[124,143],"improvement":[125],"12.2%":[127],"compared":[128],"baseline,":[131],"addition":[133],"controls":[141],"decrease":[142],"6.5%,":[145],"showing":[146],"effectiveness":[148],"adding":[150],"these":[151],"parameters.":[152],"Audio":[153],"samples":[154],"are":[155],"available":[156],"at":[157],"https://mohammadelc.github.io/SpeechGroupUKY/":[158]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}