Vishnu Panikar, Kailas Kendre, and Sachin Patekar

Deaf and dumb people's communicate their thoughts using sign language, which is a visual language. Unlike vocal communication, sign language makes use of body language and physical communication to fluidly express a person's thoughts. It can be used by someone who has trouble communicating or by a person who can hear but can not speak and also, by normal people to communicate with hearing disabled people. For deaf individuals, sign language is a very important factor for their growth. Our project aims to bridge the gap between these Deaf people and normal people with the advent of new technologies of web applications, Machine Learning, and Natural Language Processing. The main purpose of this project is to build an interface that accepts Audio/Voice as input and converts them to corresponding Sign Language for Deaf people. It is accomplished by incorporating hand forms, orientation, and movement of the hands, limbs, or body at the same time. The user interface is divided into two steps, first converting Audio to Text using speech to text API (webkitSpeechRecognition api) and secondly, represent the text using Parse Trees and applying the semantics of Natural Language Processing (NLTK specifically) for the lexical analysis of Sign Language Grammar. The work builds upon the rules of ISL(Indian Sign Language) and follows the ISL rules of Grammar

https://doi.org/10.58357/jedcs.2022.v1.i2.5