Hidden Markov Model-Based Sign Language to Speech Conversion System in TAMIL

Quick-eared and articulately speaking people convey their ideas, thoughts, and experiences by vocally interacting with the people around them. The difficulty in achieving the same level of communication is high in the case of the deaf and mute population as they express their emotions through sign language. An ease of communication between the former and the latter is necessary to make the latter an integral part of the society. The aim of this work is to develop a system for recognizing the sign language, which will aid in making this necessity a reality. In the proposed work an accelerometer-gyroscope sensor-based hand gesture recognition module is developed to recognize different hand gestures that are converted to Tamil phrases and an HMM-based text-to-speech synthesizer is built to convert the corresponding text to synthetic speech.