UKZN graduate develops AI system that translates SA Sign Language into speech
A UKZN engineering graduate has developed an AI prototype that recognises selected South African Sign Language signs and converts them into speech in real time.
An artificial intelligence system developed by a University of KwaZulu-Natal (UKZN) graduate can translate South African Sign Language (SASL) into speech in real-time. Akhil Hansrajh, a BSc Engineering graduate in Computer Engineering, created the SASL-to-Speech Translation System as his final-year design project. The system uses computer vision and machine learning to track body landmarks and identify signs, then translates them into speech using text-to-speech technology.
Dr Sulaiman Patel, Hansrajh's supervisor, noted that this was one of the first assistive technology projects in UKZN's EECE discipline to focus on South African sign language. SASL has recently been recognized as South Africa's 12th official language. The project was personally meaningful for Hansrajh, as both his parents are hard of hearing and face communication barriers in daily life.
With a fully developed system, Hansrajh aims to empower people who are hard of hearing to communicate more independently without requiring the other party to learn SASL. Despite facing mental health challenges during his studies, Hansrajh received support from his supervisors and completed his project, earning a highly commended award from the EECE.
He now plans to further develop the system, focusing on word recognition and fluent speech production. In the future, Hansrajh aspires to pursue a career in software, networking, artificial intelligence, or machine learning.
Written by urgent.news from IOL's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
