A Survey on Deep Learning based Lip-Reading Techniques

Abstract

Lip reading is a way of using skills and knowledge to understand a speaker's verbal communication by visually interpreting the lip movements of the people. This becomes a tedious task when there are obstructions or background noise in the data. Over the decade, with the buzz of Deep learning there has been an increasing demand for developing systems that can help mankind by converting speech to text. Lip reading systems are those intelligent automated systems which on looking at the face of the user try to comprehend what he/she is trying to convey and represent it visually. This process can be done by using various deep learning algorithms to detect the face, localize the lips, extract the features, train the classifier to detect the lip movement and finally convert into text. This survey paper presents a summary of various deep learning techniques, different datasets, adopted methodologies by highlighting their performance and limitations in the speech and vision applications.