{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/127266"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/127266","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Enhancing speech technology accessibility for individuals with Parkinson’s","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms","abstract_has_math":false,"creators":["Zheng, Xiuwen"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Hasegawa-Johnson, Mark Allan"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-12","date_published":"2024-12","updated_at":"2026-07-22T22:25:03Z","subjects":["Accessibility","Automatic Speech Recognition","Dysarthria"],"languages":["en","eng"],"rights":["Copyright 2024 Xiuwen Zheng"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/127266","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Hasegawa-Johnson, Mark Allan"]},{"key":"dc:creator","label":"Author","values":["Zheng, Xiuwen"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-12","2024-12-06"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Accessibility","Automatic Speech Recognition","Dysarthria"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2024 Xiuwen Zheng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/127266"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms","The student, Xiuwen Zheng, accepted the attached license on 2024-12-04 at 09:28.","The student, Xiuwen Zheng, submitted this Thesis for approval on 2024-12-04 at 09:29.","This Thesis was approved for publication on 2024-12-06 at 11:45.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21492 on 2025-03-28 at 14:28:02","Accessibility is a human right. While automatic speech recognition (ASR) has been widely used in our daily life, it struggles when recognizing dysarthric and dysphonic speech, due to acoustic impairment and lack of available training data. This thesis aims to enhance speech accessibility for people with Parkinson's, by fine-tuning pre-trained ASR systems using the 2023-10-05 data package collected by the Speech Accessibility Project (SAP), which includes speech data from 253 individuals with Parkinson's disease. The proposed method significantly outperforms a baseline model fine-tuned with typical speech, yielding improvements in word error rate of 45.15% to 38.76% compared to models fine-tuned with 100 hours and 960 hours of Librispeech data, respectively. Furthermore, this research explores cluster-dependent fine-tuning and multi-task learning methods that have shown effectiveness in the previous research in addressing speech impairments associated with Cerebral Palsy. The most promising results were obtained using a multi-task learning approach, in which the ASR model is trained to predict the speaker's impairment severity as an auxiliary task."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Enhancing speech technology accessibility for individuals with Parkinson’s"]}]}],"canonical_facts":{"dc:contributor":["Hasegawa-Johnson, Mark Allan"],"dc:creator":["Zheng, Xiuwen"],"dc:date":["2024-12","2024-12-06"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms","The student, Xiuwen Zheng, accepted the attached license on 2024-12-04 at 09:28.","The student, Xiuwen Zheng, submitted this Thesis for approval on 2024-12-04 at 09:29.","This Thesis was approved for publication on 2024-12-06 at 11:45.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21492 on 2025-03-28 at 14:28:02","Accessibility is a human right. While automatic speech recognition (ASR) has been widely used in our daily life, it struggles when recognizing dysarthric and dysphonic speech, due to acoustic impairment and lack of available training data. This thesis aims to enhance speech accessibility for people with Parkinson's, by fine-tuning pre-trained ASR systems using the 2023-10-05 data package collected by the Speech Accessibility Project (SAP), which includes speech data from 253 individuals with Parkinson's disease. The proposed method significantly outperforms a baseline model fine-tuned with typical speech, yielding improvements in word error rate of 45.15% to 38.76% compared to models fine-tuned with 100 hours and 960 hours of Librispeech data, respectively. Furthermore, this research explores cluster-dependent fine-tuning and multi-task learning methods that have shown effectiveness in the previous research in addressing speech impairments associated with Cerebral Palsy. The most promising results were obtained using a multi-task learning approach, in which the ASR model is trained to predict the speaker's impairment severity as an auxiliary task."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/127266"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 Xiuwen Zheng"],"dc:subject":["Accessibility","Automatic Speech Recognition","Dysarthria"],"dc:title":["Enhancing speech technology accessibility for individuals with Parkinson’s"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:03Z"}