A New Sign Language Translation System Based on Expert Model

Abstract. The linguistic diversity of sign languages across regions presents significant challenges for the development of accurate and culturally sensitive recognition systems. To address this, This paper propose a modular sign language recognition system that detects the regional origin of a sign language and uses specialized sub-models for translation, bypassing the limitations of generalized models. This approach allows for more precise translations by catering to regional variations, ensuring higher accuracy and preserving cultural nuances.This paper also explore the creation of a standardized, diverse dataset, integrating multiple sign languages, which serves as the foundation for the systems region detection process. The dataset was meticulously annotated, normalized, and augmented to support robust model training. By adopting sub-models and utilizing region-specific data, the system improves efficiency and scalability, offering a practical solution for real-world sign language translation. This work emphasizes the importance of preserving sign language diversity while enhancing the usability and adaptability of recognition systems.