IMPLEMENTATION OF INTELLIGENT TEXT-TO-SPEECH AI READING ASSISTIVE SYSTEM

EDEH, SAMUEL CHINAGOROM (2026) IMPLEMENTATION OF INTELLIGENT TEXT-TO-SPEECH AI READING ASSISTIVE SYSTEM. Other thesis, GODFREY OKOYE UNIVERSITY, ENUGU,.

[img] Text
EDEH SAMUEL CHINAGOROM full project-1.pdf
Download (845kB)

Abstract

This project presents the design and development of an Intelligent Text-to-Speech (TTS) Assistive Reading System that leverages Artificial Intelligence (AI), Natural Language Processing (NLP), Optical Character Recognition (OCR), and speech synthesis technologies to improve accessibility and reading efficiency for users with visual impairments, dyslexia, and other reading difficulties. This system is developed to provide speech rendering capabilities to convert text from various types of input documents including digital documents, web pages, and images into natural speech. The research attempts to resolve the limitations of existing reading assistance applications that include robotic sounding voice, low level of customizability, difficult word pronouncing capability, and inability to process scanned and handwritten documents. In order to solve the identified issues, the suggested solution includes the use of OCR technology for text extracting, NLP for processing and analyzing text and a hybrid TTS technology for generating natural speech. User customization possibilities include selecting voice, setting speech rate and language. The development was conducted with the help of Python programming language along with Flask web application framework. Tesseract OCR, pyttsx3 for offline speech synthesis, HTML5, CSS3, Bootstrap and JavaScript were used as supportive technologies for UI. Also, the structure of the database system has been created to manage user information, documents, preferences, bookmarks, and playback history. System testing was done using the methods of unit testing and integration testing in order to test performance, accuracy, and usability. It was found that the system works well in transforming various forms of data into speech and at the same time it is accurate and usable. It improves learning by enhancing comprehension and accessability through audio and text synchronization. In conclusion, the Intelligent Text-to-Speech Assistive Reading System demonstrates how AI-driven technologies can be combined to create inclusive educational tools that promote independent learning and equal access to information for all users.

Item Type: Thesis (Other)
Subjects: Q Science > Q Science (General)
Divisions: Faculty of Computing And Information Technology (FACIT)
Depositing User: Nnenna Ayo
Date Deposited: 10 Aug 2026 11:35
Last Modified: 10 Aug 2026 11:54
URI: http://eprints.gouni.edu.ng/id/eprint/6228

Actions (login required)

View Item View Item
GOUNI Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.