Next-Gen Communication: AI-driven Speech-to-Sign Language Translation

Abstract

Accessibility to digital content is challenging for individuals with hearing impairments as it lacks sign language translation. This limitation impacts their ability to consume digital resources available in audio or video format, which creates an accessibility gap. To bridge this gap, our project introduces an AI-powered system that converts Video to sign language animation using an avatar. The system integrates NLP, CNN, Speech recognition API and various libraries in its internal conversion steps from processing inputs till generating gestures by the avatar to ensure accurate and efficient translation. This paper discusses the system's design, development and evaluation for its effectiveness in making digital content more accessible.