Exploring the Efficacy of an AI-Powered Text-to-Speech Optical Character Recognition (TTS OCR) System for Enhancing Accessibility among Visually Impaired Users (with a specific focus on the Shona language)
- Author
- Kaundikiza, Munashe Brian
- Title
- Exploring the Efficacy of an AI-Powered Text-to-Speech Optical Character Recognition (TTS OCR) System for Enhancing Accessibility among Visually Impaired Users (with a specific focus on the Shona language)
- Abstract
-
Abstract
This study delves into the exploration of an AI-powered Text-to-Speech Optical Character Recognition (TTS OCR) system, specifically designed to enhance accessibility for visually impaired individuals by converting Shona text into synthesized speech. Leveraging Artificial Neural Networks within the realm of Artificial Intelligence (AI), the research scrutinizes the effectiveness of the system in emulating naturalness and intelligibility akin to human speech patterns. Through the development and evaluation of the TTS OCR system, which caters to the unique linguistic nuances of Shona language, this research endeavours to elucidate the extent to which AI technologies have advanced in replicating human-like voices. By assessing the system's capability to accurately recognize and vocalize Shona text, the study aims to ascertain its efficacy in providing seamless access to printed materials for visually impaired users. Ultimately, the findings of this research contribute valuable insights into the ongoing efforts to enhance accessibility and inclusivity for individuals with visual impairments, shedding light on the potential of AI-driven solutions to bridge the accessibility gap in multilingual contexts.
- Date
- JUNE 2024
- Publisher
- BUSE
- Keywords
- AI-powered Text-to-Speech Optical Character Recognition (TTS OCR), Leveraging Artificial Neural Networks,
- Supervisor
- Mr. T. Mhlanganiso
- Item sets
- Department of Computer Science
- Media
-
Munashe Brian Kaundikiza