{"id":"https://openalex.org/W4409156561","doi":"https://doi.org/10.1109/ieeeconf60004.2024.10942692","title":"Improving End-to-End Speech Recognition for Dysarthric Speech through In-Domain Data Augmentation","display_name":"Improving End-to-End Speech Recognition for Dysarthric Speech through In-Domain Data Augmentation","publication_year":2024,"publication_date":"2024-10-27","ids":{"openalex":"https://openalex.org/W4409156561","doi":"https://doi.org/10.1109/ieeeconf60004.2024.10942692"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf60004.2024.10942692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf60004.2024.10942692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 58th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.19797","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106638699","display_name":"Paban Sapkota","orcid":null},"institutions":[{"id":"https://openalex.org/I101326570","display_name":"National Institute of Technology Sikkim","ror":"https://ror.org/04pam3b03","country_code":"IN","type":"education","lineage":["https://openalex.org/I101326570"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Paban Sapkota","raw_affiliation_strings":["National Institute of Technology Sikkim,Department of Electronics and Communication Engineering,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Sikkim,Department of Electronics and Communication Engineering,India","institution_ids":["https://openalex.org/I101326570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003438160","display_name":"Hemant Kumar Kathania","orcid":"https://orcid.org/0000-0002-6367-5203"},"institutions":[{"id":"https://openalex.org/I101326570","display_name":"National Institute of Technology Sikkim","ror":"https://ror.org/04pam3b03","country_code":"IN","type":"education","lineage":["https://openalex.org/I101326570"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant Kumar Kathania","raw_affiliation_strings":["National Institute of Technology Sikkim,Department of Electronics and Communication Engineering,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Sikkim,Department of Electronics and Communication Engineering,India","institution_ids":["https://openalex.org/I101326570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080870546","display_name":"Sudarsana Reddy Kadiri","orcid":"https://orcid.org/0000-0001-5806-3053"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudarsana Reddy Kadiri","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory (SAIL),Los Angeles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory (SAIL),Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104114055","display_name":"Shrikanth Narayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory (SAIL),Los Angeles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory (SAIL),Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7615,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88122458,"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":"345","last_page":"349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9743000268936157,"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":0.9743000268936157,"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":0.9674999713897705,"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":0.9305999875068665,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8076111078262329},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7055627703666687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7053977251052856},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4450167119503021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32491177320480347},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07685893774032593}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8076111078262329},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7055627703666687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7053977251052856},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4450167119503021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32491177320480347},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07685893774032593},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ieeeconf60004.2024.10942692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf60004.2024.10942692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 58th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.19797","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.19797","pdf_url":"https://arxiv.org/pdf/2606.19797","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2606.19797","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19797","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.19797","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.19797","pdf_url":"https://arxiv.org/pdf/2606.19797","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W253551670","https://openalex.org/W1494198834","https://openalex.org/W2018363392","https://openalex.org/W2118379083","https://openalex.org/W2127141656","https://openalex.org/W2140567543","https://openalex.org/W2159300614","https://openalex.org/W2547793174","https://openalex.org/W2590950569","https://openalex.org/W2755431812","https://openalex.org/W2889162002","https://openalex.org/W2936861580","https://openalex.org/W2947791728","https://openalex.org/W2979826702","https://openalex.org/W2995181338","https://openalex.org/W3015611303","https://openalex.org/W3103334733","https://openalex.org/W4210482569","https://openalex.org/W4224315877","https://openalex.org/W4225855594","https://openalex.org/W4297030419","https://openalex.org/W4308383482","https://openalex.org/W4319862670","https://openalex.org/W4372263660","https://openalex.org/W4372338196","https://openalex.org/W4385764034","https://openalex.org/W4385823463","https://openalex.org/W4388677733","https://openalex.org/W4391825007","https://openalex.org/W4392909075","https://openalex.org/W4395661434","https://openalex.org/W4400275735","https://openalex.org/W6775713988","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W4404782863"],"abstract_inverted_index":{"Dysarthric":[0],"speech":[1,17,41],"recognition":[2,42],"is":[3],"crucial":[4],"for":[5,38,69,77,115,139,165],"facilitating":[6],"effective":[7],"communication":[8],"among":[9],"individuals":[10],"with":[11,52,151,162],"dysarthria.":[12,107],"However,":[13],"accurately":[14],"recognizing":[15],"dysarthric":[16,39,78,190],"poses":[18],"significant":[19],"challenges":[20,62],"due":[21],"to":[22,103],"varying":[23],"severity":[24,57,117,144,167],"levels":[25],"and":[26,66,96,156,161,176],"limited":[27],"data":[28,35,64,71,84],"availability.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,80,123],"explore":[34],"augmentation":[36,85,141,186],"techniques":[37],"automatic":[40],"(ASR)":[43],"systems":[44,76],"by":[45],"fine-tuning":[46,73,126],"the":[47,61,67,128,182,185],"End-to-End":[48],"pre-trained":[49,74],"Wav2Vec2":[50,113],"model,":[51],"a":[53],"specific":[54],"focus":[55],"on":[56],"levels.":[58,145],"To":[59],"address":[60],"of":[63,106,127,173,184],"scarcity":[65],"need":[68],"extensive":[70],"in":[72,188],"ASR":[75,129,191],"speech,":[79],"investigate":[81],"four":[82],"prominent":[83],"methods:":[86],"Speaking-Rate":[87],"Modification":[88,91,94],"(SRM),":[89],"Pitch":[90],"(PM),":[92],"Formant":[93],"(FM),":[95],"vocal":[97],"tract":[98],"Length":[99],"Perturbation":[100],"(VTLP),":[101],"tailored":[102],"different":[104],"aspects":[105],"The":[108,146],"study":[109],"uses":[110],"individually":[111],"fine-tuned":[112],"models":[114],"each":[116,140],"class":[118],"as":[119],"baseline":[120],"systems.":[121],"Additionally,":[122],"conducted":[124],"severity-specific":[125],"model":[130],"using":[131],"augmented":[132],"data.":[133],"Results":[134],"demonstrate":[135],"distinct":[136],"efficacy":[137],"patterns":[138],"technique":[142],"across":[143],"best":[147],"WERs":[148],"were":[149],"achieved":[150],"SRM":[152],"(s=0.8)":[153],"low":[154],"(9.02%)":[155],"medium":[157],"(38.11":[158],"%)":[159],"severities,":[160],"PM":[163],"(\u03c4=0.8)":[164],"high":[166],"(55.15":[168],"%),":[169],"reflecting":[170],"relative":[171],"improvements":[172],"30.02%,":[174],"16.64%,":[175],"15.47%,":[177],"respectively.":[178],"These":[179],"results":[180],"confirm":[181],"effectiveness":[183],"methods":[187],"improving":[189],"performance.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}