2-way Arabic Sign Language Translator using CNNLSTM Architecture and NLP
Tushar L. Agrawal, Siddhaling Urolagin · 2020
Over 466 million (5%) people across the world are suffering from hearing impairment, according to the World Health Organization. There is a great need to bridge the communication gap between the deaf and the general population. In our research work, recent developments such as Natural Language Processing (NLP) and Deep Learning Neural Network (DLNN) are utilized to bridge this gap. We developed a 2-way sign language translator for the Arabic language, which translates text to sign and vice versa. The NLP such as parsing, part of speech tagging, tokenization and translation are developed to achieve text to sign translation. The Convolutional Neural Network (CNN) along with Long Short-Term Memory (LSTM) is used to perform sign to text translation.