{"id":"https://openalex.org/W3208081382","doi":"https://doi.org/10.1109/sped53181.2021.9587372","title":"Dysarthric Speech Augmentation Using Prosodic Transformation and Masking for Subword End-to-end ASR","display_name":"Dysarthric Speech Augmentation Using Prosodic Transformation and Masking for Subword End-to-end ASR","publication_year":2021,"publication_date":"2021-10-13","ids":{"openalex":"https://openalex.org/W3208081382","doi":"https://doi.org/10.1109/sped53181.2021.9587372","mag":"3208081382"},"language":"en","primary_location":{"id":"doi:10.1109/sped53181.2021.9587372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped53181.2021.9587372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/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":true,"raw_author_name":"Mohammad Soleymanpour","raw_affiliation_strings":["University of Kentucky, Lexington, KY, USA"],"affiliations":[{"raw_affiliation_string":"University of Kentucky, Lexington, KY, USA","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":["University of Kentucky, Lexington, KY, USA"],"affiliations":[{"raw_affiliation_string":"University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"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":["Marquette University, Milwaukee, WI, USA"],"affiliations":[{"raw_affiliation_string":"Marquette University, Milwaukee, WI, USA","institution_ids":["https://openalex.org/I102461120"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064273942"],"corresponding_institution_ids":["https://openalex.org/I143302722"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69361098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"46"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9977999925613403,"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/speech-recognition","display_name":"Speech recognition","score":0.8413259983062744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7238363027572632},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6429002285003662},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5963936448097229},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.44878366589546204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3358907699584961},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07664093375205994}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8413259983062744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7238363027572632},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6429002285003662},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5963936448097229},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.44878366589546204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3358907699584961},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07664093375205994},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped53181.2021.9587372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped53181.2021.9587372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1597628276","https://openalex.org/W1855892484","https://openalex.org/W1973592590","https://openalex.org/W2018363392","https://openalex.org/W2140360678","https://openalex.org/W2581309910","https://openalex.org/W2749128330","https://openalex.org/W2792759062","https://openalex.org/W2799800213","https://openalex.org/W2888789389","https://openalex.org/W2889469831","https://openalex.org/W2936774411","https://openalex.org/W2962824709","https://openalex.org/W3014344307","https://openalex.org/W3014690389","https://openalex.org/W3015210890","https://openalex.org/W3097720583","https://openalex.org/W3134043075","https://openalex.org/W3157063407","https://openalex.org/W3163725792","https://openalex.org/W3200199839","https://openalex.org/W6639156005","https://openalex.org/W6785297517"],"related_works":["https://openalex.org/W1970025505","https://openalex.org/W2030358499","https://openalex.org/W1966585405","https://openalex.org/W2093863013","https://openalex.org/W2046078639","https://openalex.org/W2493561494","https://openalex.org/W2069086801","https://openalex.org/W2026861386","https://openalex.org/W2592942120","https://openalex.org/W2041543977"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,27,80,115,135],"recognition":[2],"systems":[3],"are":[4],"effective,":[5],"but":[6],"in":[7],"order":[8],"to":[9,45,81,100],"train":[10],"an":[11,50],"end-to-end":[12,51],"model,":[13],"a":[14,40,98],"large":[15],"amount":[16],"of":[17,49,78,133],"training":[18],"data":[19,42],"is":[20],"needed.":[21],"For":[22],"applications":[23],"such":[24,85],"as":[25,86],"dysarthric":[26,52,134],"recognition,":[28],"we":[29,38,96],"do":[30],"not":[31],"have":[32],"sufficient":[33],"data.":[34],"In":[35],"this":[36],"paper,":[37],"propose":[39],"specialized":[41],"augmentation":[43],"approach":[44,60],"enhance":[46],"the":[47,73,101,130],"performance":[48],"ASR":[53],"based":[54],"on":[55],"sub-word":[56],"models.":[57],"The":[58],"proposed":[59],"contains":[61],"two":[62],"methods,":[63],"including":[64],"prosodic":[65,83,117],"transformation":[66,71,118],"and":[67,76,89,93,125,129,141],"time-feature":[68],"masking.":[69],"Prosodic":[70],"modifies":[72],"speaking":[74],"rate":[75],"pitch":[77],"normal":[79,114],"control":[82],"characteristics":[84],"loudness,":[87],"intonation,":[88],"rhythm.":[90],"Using":[91],"time":[92],"feature":[94],"masking,":[95],"apply":[97],"mask":[99],"Mel":[102],"Frequency":[103],"Cepstral":[104],"Coefficients":[105],"(MFCC)":[106],"for":[107],"robustness-focused":[108],"augmentation.":[109],"Results":[110],"show":[111],"that":[112],"augmenting":[113],"with":[116],"plus":[119],"masking":[120,136],"decreases":[121,137],"CER":[122,138],"by":[123,127,139,143],"5.4%":[124],"WER":[126,142],"5.6%,":[128],"further":[131],"addition":[132],"11.3%":[140],"11.4%.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}