Speech to Sign Language Conversion System

Overview

This project implements a real-time Speech-to-Sign Language conversion pipeline. The system captures spoken input, converts speech to text using Automatic Speech Recognition (ASR), processes the text into gloss format, and renders corresponding sign language videos.

System Pipeline

Microphone Input
↓
Speech Recognition (Google ASR)
↓
Text Preprocessing
↓
Gloss Generation
↓
Word-to-Video Mapping
↓
Video Rendering (OpenCV)

Features

• Real-time speech recognition
• Automatic speech-to-text conversion
• Gloss-based text processing
• Word-to-video mapping using 152 sign clips
• Continuous listening mode
• Voice command exit ("exit", "stop", "quit")

Technologies Used

• Python
• SpeechRecognition
• PyAudio
• OpenCV
• Google Speech Recognition API

Project Structure