top of page

Performance Evaluation of Automatic Speech Recognition for ImpairedSpeech (Dysarthria)

Writer's picture: Questioz EditorQuestioz Editor

Performance Evaluation of Automatic Speech Recognition for Impaired

Speech (Dysarthria) People Based on IDEA and CLIPS Data


Author : Shivansh Kulshrestha


Abstract

Dealing with a speech impairment is a severe challenge for Automatic Speech Recognition (ASR) systems since dysarthria renders conventional methods ineffective. Specifically, this study aims to validate whether a unique speech analysis technique can be applied to dysarthria speakers. ASR system efficacy can be enhanced using a unique method that optimizes distinct spectral analysis parameters employed to determine the optimal regions. Further, it investigates the relationship between the speaker's vocal features and window-shift parameters that optimizes ASR systems for specific speakers to minimize error. The current study used a speech impairment dataset containing both normal and damaged vocals. The IDEA database contained 30 dysarthria speakers, whereas the CLIPS database contained 10 speaker vocals. These data exist in both databases and can be accessed freely. The dataset collected from these databases was initially checked for quality, and only the vocals of good quality were included in this study. The experimental analysis was performed.

The results demonstrated that when a vocal has dysarthria, a normal ASR system can perform better using speech analysis. Otherwise, the new method showed poor performance when speech is unimpaired or only minimally impaired. At last, the study findings indicated that a significant correlation existed between the vocal of the selected speaker and optimal parameters.




Recent Posts

See All

Comparison of urban layouts

Siddharth Jain ABSTRACT The present study provides a comprehensive analysis and comparison of the transportation networks in three of the...

Komentāri


Volume 1

Volume 2

Contact Us
Email ID - editor.questioz@gmail.com

Terms and Conditions

Questioz cannot be held responsible for any violation of academic integrity. The intellectual property of all contributing researchers will be respected and protected. Questioz reserves the non-exclusive right to republish submitted material with attribution to the author in any other format, including all print, electronic and online media. However, all individual contributors to Questioz retain the right to submit their work for non-exclusive publication elsewhere.

© 2023 by The Thomas Hill. Proudly created with Wix.com

bottom of page