TSLFormer: A Lightweight Transformer Model for Turkish Sign Language Recognition Using Skeletal Landmarks

TL;DR

TSLFormer is a lightweight transformer-based model that recognizes Turkish Sign Language from skeletal joint data, enabling efficient, real-time gesture translation without raw video input.

Contribution

The paper introduces TSLFormer, a novel transformer model that uses skeletal joint data for sign language recognition, reducing computational complexity and improving efficiency.

Findings

Achieves competitive accuracy on AUTSL dataset

Operates with minimal computational resources

Enables real-time sign language translation

Abstract

This study presents TSLFormer, a light and robust word-level Turkish Sign Language (TSL) recognition model that treats sign gestures as ordered, string-like language. Instead of using raw RGB or depth videos, our method only works with 3D joint positions - articulation points - extracted using Google's Mediapipe library, which focuses on the hand and torso skeletal locations. This creates efficient input dimensionality reduction while preserving important semantic gesture information. Our approach revisits sign language recognition as sequence-to-sequence translation, inspired by the linguistic nature of sign languages and the success of transformers in natural language processing. Since TSLFormer uses the self-attention mechanism, it effectively captures temporal co-occurrence within gesture sequences and highlights meaningful motion patterns as words unfold. Evaluated on the AUTSL dataset with over 36,000 samples and 227 different words, TSLFormer achieves competitive performance with minimal computational cost. These results show that joint-based input is sufficient for enabling real-time, mobile, and assistive communication systems for hearing-impaired individuals.