Real-time converting recognized text into voice

Mohd Razeef, Mohamad Danial Uzaeer (2022) Real-time converting recognized text into voice. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

Text (Full Text) Real-time converting recognized text into voice.pdf - Submitted Version Download (1MB)

Abstract

The goal of this project is to create an algorithm that converts text into speech. Most of the work involves coding and software. The algorithm built should be able to convert recognized text from an image captured into speech. According to studies, text-to-speech conversion is extremely beneficial for persons who have difficulty reading. Various experiments are being carried out, as well as a few techniques gained from the research. The research problem statement as well as the project's goals have been determined. The study's scope has been discussed. In the literature review chapter, every aspect of the project and study has been thoroughly explained. This project combines a few approaches, and it is divided into four sections: camera captured image, optical character recognition, language translation, and text to speech. Each component uses a different technique. In the methodology chapter, the development of real-time conversation recognized text to speech is covered. The system was then put to the test, with accuracy and code execution time being measured. This project is running smoothly and achieving all its goals.

Actions (login required)

View Item