Transformer Based Sign-to-Text Translation For Bangladeshi Sign Language

Effective communication is a fundamental human need, yet millions of deaf individuals worldwide face significant barriers when interacting with the non-deaf population. Our research addresses this challenge by developing an innovative system that utilizes Natural Language Processing (NLP) techniques to interpret and translate sign language into a format easily understood by individuals who are deaf or hard of hearing. Building on the legacy of assistive technologies, such as the pioneering work in 1977 that enabled the translation of sign language into English via a mechanical hand, our approach aims to modernize and expand these efforts. We have developed a Custom Transformer Encoder Stack Model, trained on a dataset comprising 102 Bangladeshi Sign Language (BdSL) signs. The model achieved exceptional results, with 99.52% accuracy on the training dataset and 98.12% on the test dataset, demonstrating its precision and robustness. Furthermore, the system's adaptability allows for integrating other sign languages through updates to the dataset, making it a flexible and scalable solution for real-time communication. Our research aims to foster greater inclusivity by providing a tool that empowers deaf individuals to communicate seamlessly with the hearing community, thereby enhancing accessibility, social integration, and overall communication equity.