Visual Speech Recognition using VGG16 Convolutional Neural Network

Abstract

Communication is all about expressing one’s thoughts to another person through speech and facial expressions. But for people with hearing impairment, it is difficult to communicate without any assistance. In most of these cases Visual speech recognition (VSR) systems simplify the tasks by using Machine Learning algorithms and assisting them to understand speech and socialize without depending on the auditory perception. Thus, one can visualize VSR system as a lifeline for people with hearing impairment which helps them in providing a way to understand the words that are being tried to convey to them through speech. In this work we used VGG16 convolutional neural network architecture for Kannada and English datasets. We used custom dataset for the research work and got the accuracy of 90.10% for English database and 91.90% for Kannada database.