Leveraging NLP for Generating Coherent Sentences in Sign Language Translation Systems

Sign language is an essential communication tool for the deaf and mute community, yet significant barriers remain when interacting with non-signers, often hindering effective communication. In order to translate sign language motions into comprehensible English sentences, the creation of an AI-powered sign language recognition system that makes use of Natural Language Processing (NLP) is investigated in this study. Leveraging deep learning models and NLP techniques, the system aims to bridge the communication gap, making sign language more accessible to non-signers. This work introduces a novel LSTM-based model that leverages advanced tokenization and sequence padding to convert hand gestures into text. Achieving the highest accuracy of 84%, the system demonstrates its potential to improve communication in both casual and professional settings. The results pave the way for future developments in assistive technology by highlighting the contribution of AI in enhancing inclusion and facilitating accessibility for individuals who are Deaf or Mute.