MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202641081620 A) filed by Vallurupalli Nageswara Rao Vignana Jyothi Institute Of Engineering Technology on July 02, 2026, for Real-Time Emotion-Aware Speech Translation System Using Prosody-Conditioned Speech Synthesis.
Inventors include Dr. Harshavardhan Awari; A. Kaushik; G. Krishna Anirudh; J. Rikhil Rao; N. V. Abhijeet Mukund; and Navaneeth Reddy N.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: The present invention discloses an emotion-aware prosody-preserving speech-to-speech translation system that maintains the expressive qualities of the original speech while converting it from a source language to a target language. This innovative framework integrates advanced modules for prosody and emotion extraction, automatic speech recognition, neural machine translation, and prosody-conditioned text-to-speech synthesis to deliver natural, emotionally consistent, and speaker-identity-preserving output. By transferring critical paralinguistic features such as pitch, rhythm, energy, and emotional tone alongside linguistic content, the system overcomes the robotic and monotonous limitations of traditional translation tools. Designed for real-time operation with modular architecture and efficient model deployment, it achieves high fidelity in multilingual scenarios, including low-resource languages, making it a valuable advancement for cross-cultural communication, accessibility, and interactive applications.
Disclaimer: Curated by HT Syndication.
