Copyright © 2025 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{178607,
        author = {Harsh Tyagi and Jaivardhan Saini and Gaurav Yadav and Saksham Pandey and Ms. Vani Rastogi},
        title = {Innovative AI Solution for Real-Time Translation of Dynamic Sequential Sign Language},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {4108-4112},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178607},
        abstract = {This paper introduces a system to convert Indian Sign Language (ISL) gestures into text and speech,helping to address communication challenges for the Mutism impaired. The system employs state-of-the-art computer vision and natural language processing techniques with MediaPipe to perform pose detection and key point extraction from 30-second video segments on upper-body landmarks. These keypoints are processed by the Long Short-Term Memory (LSTM) network for categorizing gestures to ISL words or phrases. For perfect coherence with the grammar of English, it has the refinement output to be carried out through the transformer-based language model Gemma Model. It operates on four different stages, that is video capture, extraction of key points, classification through LSTM to ISL gestures, and conversion to speech from text using edge_tts library. The system's ability to combine pose estimation with sequential modeling accurately interprets the ISL gestures, bringing out grammatically correct text and speech. The system manifests high accuracy in gesture-to-text translation and real-time performance, allowing for flawless communication between mutism-impaired individuals and others. Such innovation enhances inclusivity in that it converts ISL gestures into accessible text and speech, contributing to broader participation in society and breaking through barriers of communication.},
        keywords = {Gemma, ISL, LSTM, Mediapipe, Mutism, Transformer},
        month = {May},
        }