Vision-Based Real-Time Gesture to Speech & Speech to Text Translation for Sign Language
The proposed system aims to reduce communication barriers for individuals with hearing or speech impairments using a real-time, vision-based gesture-to-speech and speech-to-text translation system. It captures hand gestures through a webcam, processes images using OpenCV, and recognizes gestures using a Convolutional Neural Network (CNN) to generate text and speech through pyttsx3. Additionally, spoken input is converted into text using the Speech-Recognition library. The system integrates both functionalities into a single application to enable accessible and effective communication between sign language users and non-sign language users. By providing two-way communication support, the proposed approach helps users interact more conveniently in everyday situations. The use of real-time image processing enables continuous gesture detection and recognition. Furthermore, the system aims to provide a simple, user-friendly, and cost-effective solution without requiring specialized hardware. This integrated approach has the potential to improve accessibility in educational institutions, workplaces, healthcare environments, and other public spaces.
Authors
- Miss. Khushi Hiwarkar Miss. Pooja Jori
- Prof. Madhavi Kolse Miss. Sanika Gadge
Institutions
- Jaihind College of Engineering (IN)
Publication Details
- Journal
- International Journal of Advanced Research in Science Communication and Technology
- Published
- 2026-11-16
- DOI
- https://doi.org/10.48175/ijarsct-40809
- Primary Topic
- Hand Gesture Recognition Systems
- Type
- article
- Field-Weighted Citation Impact
- 0.00