Year: 2025
Type: article
Abstract: Productive communication between people with speech and hearing disabilities and the general public continues to be a pressing challenge. This paper presents a survey for two-way, real-time communication systems aimed at identifying and interpreting Indian Sign Language into text and speech and speech to text. The system, through the use of a mix of computer-vision, natural- language-processing, machine-learning, and speech- processing-technologies, translates hand gestures through Natural-Language-Processing (NLP), MediaPipe and OpenCV for gesture-to-text/speech to regional language conversion and text-to-sign conversion. On the other hand, it converts text language into animated sign representations, which increase the accessibility of deaf users and subsequently when video or image is used as input it outputs corresponding text increasing communication between normal and special users. Real-time performance, high accuracy, and scalability are prioritized on the platform with affordability guaranteed via open-source tools.
Authors: Dhanush G M, Gagandeep D, Jayanth B Prakash, Aryan Eshwar K R, Nandita Bangera
Language: English
Subfield: Human-Computer Interaction
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4412824236