Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Enhancing the accessibility of voice assistants for individuals with Dysarthria through non-verbal voice cue interaction

Jaddoh, Aisha 2024. Enhancing the accessibility of voice assistants for individuals with Dysarthria through non-verbal voice cue interaction. PhD Thesis, Cardiff University.
Item availability restricted.

[thumbnail of 2024JaddohAPhD.pdf] PDF - Accepted Post-Print Version
Restricted to Repository staff only until 27 August 2025 due to copyright restrictions.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (16MB) | Request a copy
[thumbnail of Cardiff University Electronic Publication Form] PDF (Cardiff University Electronic Publication Form) - Supplemental Material
Restricted to Repository staff only

Download (395kB) | Request a copy

Abstract

This thesis presents a comprehensive exploration into the interaction between individuals with dysarthria and Smart Voice Assistants (SVAs), focusing particularly on the utilization of a novel interaction method: non-verbal voice cues, and assessing the efficacy of different interaction methods. Dysarthria, a speech disorder resulting from neurological injury, significantly impairs speech clarity, challenging those attempting to interact with SVAs that typically rely on clear verbal commands. The thesis examines the needs of users with dysarthria, firstly through a review of related literature to situate our thesis. This research examines current gaps in voice recognition technology for individuals with dysarthria and limitations in interaction. We follow this by conducting three studies to investigate the current use of SVAs by individuals with dysarthria and to evaluate the efficacy of alternative interaction methods in enhancing accessibility. Through user-centered and participatory design, we develop ’Daria,’; a bespoke system designed to use non-verbal cues, enabling users to leverage sounds they can articulate comfortably. We thereafter use Daria to further test our hypotheses. This method effectively bypasses the need for intermediary devices, thus reducing interaction fatigue and streamlining communication. We conducted comprehensive research involving three sequential studies to identifying user challenges, evaluating interaction effectiveness and command mapping, and comparing usability and user experience across different design options against alternative methods. The findings conclude that non-verbal voice cues are viable and preferred by individuals with moderate to severe dysarthria due to their simplicity and ease of use, highlighting the effectiveness of this interaction method in facilitating more reliable and efficient communication for users. The mapping approach within the system proved to be successful and memorable for users, enhancing overall system usability. Consequently, non-verbal voice cues have been identified as a highly usable technique for individuals with dysarthria, offering them an accessible and efficient user experience.

Item Type: Thesis (PhD)
Date Type: Completion
Status: Unpublished
Schools: Computer Science & Informatics
Date of First Compliant Deposit: 27 August 2024
Date of Acceptance: 22 August 2024
Last Modified: 02 Sep 2024 09:00
URI: https://orca.cardiff.ac.uk/id/eprint/171582

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics