Connecting the Dots: Leveraging Spatio-Temporal Graph Neural Networks for Accurate Bangla Sign Language Recognition
This work addresses the problem of sign language recognition for the deaf community in Bangladesh, focusing on a low-resource language, but it is incremental as it builds on existing methods for other sign languages.
The paper tackles the lack of word-level datasets and models for Bangla Sign Language by introducing BdSL40, a new dataset of 611 videos over 40 words, and achieves an F1 score of 89% using a novel Graph Neural Network approach.
Recent advances in Deep Learning and Computer Vision have been successfully leveraged to serve marginalized communities in various contexts. One such area is Sign Language - a primary means of communication for the deaf community. However, so far, the bulk of research efforts and investments have gone into American Sign Language, and research activity into low-resource sign languages - especially Bangla Sign Language - has lagged significantly. In this research paper, we present a new word-level Bangla Sign Language dataset - BdSL40 - consisting of 611 videos over 40 words, along with two different approaches: one with a 3D Convolutional Neural Network model and another with a novel Graph Neural Network approach for the classification of BdSL40 dataset. This is the first study on word-level BdSL recognition, and the dataset was transcribed from Indian Sign Language (ISL) using the Bangla Sign Language Dictionary (1997). The proposed GNN model achieved an F1 score of 89%. The study highlights the significant lexical and semantic similarity between BdSL, West Bengal Sign Language, and ISL, and the lack of word-level datasets for BdSL in the literature. We release the dataset and source code to stimulate further research.