A Comprehensive Review of Sign Language Translation for Inclusive Education Systems

Sign Language Translation (SLT) has emerged as a critical technological enabler for inclusive education systems, aiming to bridge communication gaps between hearing-impaired learners and mainstream educational environments. Recent advancements in computer vision, deep learning, and artificial intelligence have significantly improved the accuracy, robustness, and real-time feasibility of sign language recognition and translation systems. These systems increasingly support isolated signs, continuous sign language, multilingual alphabets, and sentence-level translation, making them suitable for classroom integration, e-learning platforms, and assistive educational tools. This review paper presents a comprehensive analysis of recent research on sign language translation, with a particular focus on methods applicable to inclusive education systems. The paper systematically examines state-of-the-art techniques, including YOLO-based detection, CNN–LSTM hybrids, graph convolutional networks, attention mechanisms, and optimization-driven feature reduction approaches. Key research findings, challenges, and limitations are critically discussed, highlighting gaps related to scalability, dataset diversity, real-time deployment, and educational usability. By synthesizing current trends and insights, this review aims to guide researchers and educators toward the development of more effective, accessible, and learner-centered sign language translation systems for inclusive education.