Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{180751,
        author = {Carol Maria Dsilva and Anushka and Akanksha Singh and Aastha Mishra},
        title = {Audio-Visual Translation Framework for Indian Sign   Languages Using Deep Learning and NLP},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {2251-2258},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180751},
        abstract = {This paper reviews recent developments in automatic translation systems for Indian Sign Language (ISL) by integrating deep learning and natural language processing (NLP) techniques. Motivated by the need to bridge communication gaps between the deaf and hearing communities, the study explores current methodologies such as convolutional neural networks (CNNs), long short-term memory networks (LSTMs), transformer models, and attention mechanisms. These approaches are designed to address the spatial–temporal and grammatical complexities of ISL. Additionally, innovative methods like latent space-based translation without temporal segmentation and multimodal emotion recognition are examined. Despite advancements, challenges remain in areas such as dataset diversity, integration of cultural context, and achieving real-time performance on devices with limited resources. The paper also proposes an architecture that combines visual gesture recognition (using MediaPipe for landmark extraction) with advanced NLP-driven text generation and text-to-speech conversion. This integrated framework enhances recognition accuracy and moves toward a more robust, context-aware, audio-visual ISL translation system.},
        keywords = {Indian Sign Language (ISL), deep learning, gesture recognition, natural language processing, MediaPipe.},
        month = {June},
        }