MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122171 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'multi-modal visual speech recognition system with sentiment and emotion analysis.'
Inventor(s) include Dr. Nalini N; Mr. Anurag Jawalkar; Ms. Manogna Chowdary Yamani; and Mr. Yash Singhal.
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 multi-modal visual speech recognition system including a video processing module configured to receive video input containing visual speech data and extract frames, a lip reading model configured to process frames and generate text output from visual lip movements, a sentiment analysis module configured to analyze text output and determine sentiment classification, a facial emotion recognition module configured to analyze frames and determine emotion classification, and a user interface module configured to display the text output, sentiment classification, and emotion classification. The lip reading model includes a convolutional neural network layer configured to extract spatial features and a bidirectional long short-term memory network layer configured to process temporal dependencies. The system processes video sequences of approximately 75 frames with 46 by 140 pixel dimensions in grayscale format and achieves processing latency of less than three seconds."
Disclaimer: Curated by HT Syndication.
