{"id":"https://openalex.org/W4415957642","doi":"https://doi.org/10.48550/arxiv.2510.16700","title":"Zero- and One-Shot Data Augmentation for Sentence-Level Dysarthric Speech Recognition in Constrained Scenarios","display_name":"Zero- and One-Shot Data Augmentation for Sentence-Level Dysarthric Speech Recognition in Constrained Scenarios","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415957642","doi":"https://doi.org/10.48550/arxiv.2510.16700"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2510.16700","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.16700","pdf_url":"https://arxiv.org/pdf/2510.16700","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.16700","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wang, Shiyao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Shiyao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052465353","display_name":"Shiwan Zhao","orcid":"https://orcid.org/0000-0001-5068-025X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Shiwan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101880813","display_name":"Jiaming Zhou","orcid":"https://orcid.org/0000-0002-0043-3645"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jiaming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088716214","display_name":"Yong Qin","orcid":"https://orcid.org/0000-0002-6519-8316"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Yong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9266999959945679,"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"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9266999959945679,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.04470000043511391,"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/T12684","display_name":"Stuttering Research and Treatment","score":0.0038999998942017555,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical 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/dysarthria","display_name":"Dysarthria","score":0.7723000049591064},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5871999859809875},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4788999855518341},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3935000002384186},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.3610999882221222},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3366999924182892},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.310699999332428}],"concepts":[{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.7723000049591064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.67330002784729},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5871999859809875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.574999988079071},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3580000102519989},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3366999924182892},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29030001163482666},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2621999979019165}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.16700","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.16700","pdf_url":"https://arxiv.org/pdf/2510.16700","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},{"id":"doi:10.48550/arxiv.2510.16700","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.16700","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.16700","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.16700","pdf_url":"https://arxiv.org/pdf/2510.16700","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dysarthric":[0],"speech":[1,87],"recognition":[2,88],"(DSR)":[3],"research":[4],"has":[5,69],"witnessed":[6],"remarkable":[7],"progress":[8],"in":[9,110,133,168,185],"recent":[10],"years,":[11],"evolving":[12],"from":[13,124],"the":[14,21,30,39,53,95,98,104,169],"basic":[15],"understanding":[16],"of":[17,24,34,41,55,97,171,182],"individual":[18],"words":[19],"to":[20,52,62,81,101,127,165],"intricate":[22],"comprehension":[23],"sentence-level":[25,57],"expressions,":[26],"all":[27],"driven":[28],"by":[29],"pressing":[31],"communication":[32,195],"needs":[33],"individuals":[35],"with":[36,175],"dysarthria.":[37],"Nevertheless,":[38],"scarcity":[40],"available":[42],"data":[43,66,84,100,123,154],"remains":[44],"a":[45,49,72,146],"substantial":[46,166],"hurdle,":[47],"posing":[48],"significant":[50],"challenge":[51],"development":[54],"effective":[56],"DSR":[58,172],"systems.":[59],"In":[60],"response":[61],"this":[63,141],"issue,":[64],"dysarthric":[65,113,177],"augmentation":[67],"(DDA)":[68],"emerged":[70],"as":[71],"highly":[73],"promising":[74],"approach.":[75],"Generative":[76],"models":[77,120],"are":[78,181],"frequently":[79],"employed":[80],"generate":[82],"training":[83],"for":[85,119,152,160],"automatic":[86],"tasks.":[89],"However,":[90],"their":[91],"effectiveness":[92],"hinges":[93],"on":[94,122],"ability":[96],"synthesized":[99],"accurately":[102],"represent":[103],"target":[105],"domain.":[106],"The":[107],"wide-ranging":[108],"variability":[109],"pronunciation":[111],"among":[112],"speakers":[114,126],"makes":[115],"it":[116],"extremely":[117],"difficult":[118],"trained":[121],"existing":[125],"produce":[128],"useful":[129],"augmented":[130],"data,":[131],"especially":[132],"zero-shot":[134],"or":[135],"one-shot":[136],"learning":[137],"settings.":[138],"To":[139],"address":[140],"limitation,":[142],"we":[143],"put":[144],"forward":[145],"novel":[147],"text-coverage":[148],"strategy":[149,158],"specifically":[150],"designed":[151],"text-matching":[153],"synthesis.":[155],"This":[156],"innovative":[157],"allows":[159],"efficient":[161],"zero/one-shot":[162],"DDA,":[163],"leading":[164],"enhancements":[167],"performance":[170],"when":[173],"dealing":[174],"unseen":[176],"speakers.":[178],"Such":[179],"improvements":[180],"great":[183],"significance":[184],"practical":[186],"applications,":[187],"including":[188],"dysarthria":[189],"rehabilitation":[190],"programs":[191],"and":[192],"day-to-day":[193],"common-sentence":[194],"scenarios.":[196]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-22T00:00:00"}
