Indian Sign Language to Speech Conversion Using Deep Learning

Abstract

Sign language recognition is a worldwide concern across the globe. The use of technology has a scope in aiding the necessary help in the recognition of sign language. The major challenge lies in detecting and understanding signs, as the language differs across the various geographical regions, and there are no specific rules for understanding them. Hence, this research article uses a transfer learning algorithm with TensorFlow object detection to recognize Indian sign language. The proposed model has achieved an accuracy of around 97.87% for different types of sentences used in the experimentation. The main advantage of the proposed model is that it is feasible to identify Indian sign language and produce the corresponding voice output using speech synthesis system. The system is helpful to the deaf and dumb community's society and encourages such people's upliftment.