MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122088 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'multilingual voice assistant system with fine-tuned language model for medical applications.'
Inventor(s) include Dr. Kakelli Anil Kumar; Manas Ranjan; Abhigyan Satya Das; and Parthasarathi Mohanty.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a multilingual voice assistant system for medical applications. The system includes a speech recognition module configured to convert audio input to text, supporting English and Tamil languages. The system includes a language model fine-tuned on medical data for processing medical queries and a response generation module configured to generate medical responses. The system includes a text-to-speech synthesis module configured to convert text responses to audio output with multilingual capabilities supporting English and Tamil. The speech recognition module includes audio preprocessing with noise reduction, voice activity detection, and audio normalization. The language model includes a LLaMA2 model fine-tuned using Low-Rank Adaptation techniques with 4-bit quantization to reduce memory consumption while maintaining accuracy. The system includes activation phrase detection to initiate voice interaction and session management capabilities to maintain conversation context across multiple user interactions."
Disclaimer: Curated by HT Syndication.
