MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122831 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'machine learning system for parkinson's disease diagnosis using speech signals.'
Inventor(s) include Dr. Balaji N; Mr. Harsh Kumar; Mr. Neheshreyas Bhausaheb; and Mr. Chinmay Paliwal.
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 system for automated classification of speech signals. The system includes speech signal acquisition means for capturing speech data from a user, feature extraction means for deriving acoustic parameters from the speech data, wherein the acoustic parameters include pitch, jitter, shimmer, and harmonic-to-noise ratio, and machine learning classification means for processing the acoustic parameters to generate a classification result indicating presence or absence of speech patterns associated with neurological conditions. The system may include preprocessing means for applying noise reduction and signal normalization prior to feature extraction. The machine learning classification means may include a hybrid architecture with a Vision Transformer model, Multi-Layer Perceptron network, and Random Forest classifier. The classification means may generate a confidence score indicating reliability of the classification result, and the acquisition means may be configured for real-time speech recording through a web-based interface."
Disclaimer: Curated by HT Syndication.
