BdSL-SPOTER: A Transformer-Based Framework for Bengali Sign Language Recognition with Cultural Adaptation
This work addresses accessibility for Bengali sign language users by providing an efficient recognition model, though it is incremental as it builds on the existing SPOTER paradigm.
The paper tackles the problem of Bengali Sign Language recognition by introducing BdSL-SPOTER, a transformer-based framework that achieves 97.92% Top-1 validation accuracy on the BdSLW60 benchmark, representing a 22.82% improvement over a baseline.
We introduce BdSL-SPOTER, a pose-based transformer framework for accurate and efficient recognition of Bengali Sign Language (BdSL). BdSL-SPOTER extends the SPOTER paradigm with cultural specific preprocessing and a compact four-layer transformer encoder featuring optimized learnable positional encodings, while employing curriculum learning to enhance generalization on limited data and accelerate convergence. On the BdSLW60 benchmark, it achieves 97.92% Top-1 validation accuracy, representing a 22.82% improvement over the Bi-LSTM baseline, all while keeping computational costs low. With its reduced number of parameters, lower FLOPs, and higher FPS, BdSL-SPOTER provides a practical framework for real-world accessibility applications and serves as a scalable model for other low-resource regional sign languages.