AI-Powered Deaf Companion System for Inclusive Communication Between Deaf and Hearing Individuals

Authors

  • Mahesh C Department of Computer Science and Engineering, Sri Ranganathar Institute of Engineering and Technology, Athipalayam, Coimbatore 641110, Tamil Nadu, India. Author
  • Srimathi P Department of Computer Science and Engineering, Sri Ranganathar Institute of Engineering and Technology, Athipalayam, Coimbatore 641110, Tamil Nadu, India. Author
  • Prathipa K Department of Computer Science and Engineering, Sri Ranganathar Institute of Engineering and Technology, Athipalayam, Coimbatore 641110, Tamil Nadu, India. Author
  • Polimera Haripriya Department of Computer Science and Engineering, Sri Ranganathar Institute of Engineering and Technology, Athipalayam, Coimbatore 641110, Tamil Nadu, India. Author

DOI:

https://doi.org/10.47392/IRJAEM.2026.0074

Keywords:

Artificial Intelligence (AI), Deep Learning, Temporal Convolutional Networks (TCNs), Hidden Markov Models (HMMs), Neural Networks, Computer Vision, Natural Language Processing (NLP), Sign Language Recognition, Speech-to-Text (STT), Gesture Recognition, Speech Recognition

Abstract

The AI-Powered Deaf Companion System is designed to bridge the communication gap between deaf and hearing individuals using cutting-edge deep learning technologies. Leveraging Temporal Convolutional Networks (TCNs), the Sign Recognition Module (SRM) accurately interprets sign language gestures in real time. Meanwhile, the Speech Recognition and Synthesis Module (SRSM), powered by Hidden Markov Models (HMMs), converts spoken language into text, ensuring seamless bidirectional communication. To enhance accessibility, the Avatar Module (AM) visually translates spoken text into sign language gestures, making interactions more intuitive. By integrating computer vision, natural language processing (NLP), and speech synthesis, this system fosters inclusive communication, empowering the deaf community with greater independence and interaction opportunities.

Downloads

Download data is not yet available.

Downloads

Published

2026-03-21