AI/ML-based Real-Time Sign Language Converter: Enabling Seamless Communication via Audio Calls for Deaf and Mute Individuals
Prasanthi Rathnala, Naresh Patnana, Gogineni Deekshit, Dadi Naga seshu, Rusheeta, P Megana · 2025
The increasing adoption of Artificial Intelligence (AI) and Machine Learning (ML) technologies has created new possibilities in improving accessibility and communication for people with disabilities. One of the most significant challenges faced by the deaf and mute communities is the communication barrier with non-sign language users. This paper proposes an AI/ML-based real-time sign language converter that enables seamless communication via audio calls for deaf and mute individuals. The proposed system integrates multiple components, including gesture recognition technology and computer vision, to translate sign language gestures into text and audio. The real-time converter uses machine learning models to recognize hand and facial gestures, then converts the recognized gestures into text, which is subsequently converted into speech via a text-to-speech (TTS) engine. The system also ensures minimal latency, enhancing the user experience during live interactions. Experimental results show that the system offers an efficient, real-time solution for overcoming communication barriers, fostering inclusivity and independence for deaf and mute individuals.