MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202611065679 A) filed by Graphic Era Hill University, Dehradun on May 18, 2026, for A System And Method For Real-Time Embedded Ai-Driven Voice Authentication And Deepfake Detection.
Inventors include Simar Singh Rayat; and Dr. Arun Pratap Singh Rathod.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: ABSTRACT A SYSTEM AND METHOD FOR REAL-TIME EMBEDDED AI-DRIVEN VOICE AUTHENTICATION AND DEEPFAKE DETECTION This invention relates to a real-time embedded system for voice authentication and deepfake detection in the field of digital voice processing. The system comprises a plurality of high-sensitivity microphones on an external enclosure for capturing ambient voice signals; employs a signal conditioning module with analog/digital filtering, amplification, and noise reduction to produce a conditioned audio signal; utilizes a feature extraction unit to generate digital audio feature sets, including Mel-frequency cepstral coefficients and short-time Fourier transform spectrogram components; integrates a neural classification engine with convolutional layers, gated recurrent units, and attention mechanisms for outputting experimental detection results; includes a voiceprint memory and comparison engine for trusted template matching; features an embedded processing unit on a real-time operating system, accompanied by a secure bootloader/model update module and power management circuitry. Dated this 18th day of May, 2026 (Suvarna Pandey) Regd. Patent Agent [IN/PA-1592] Of RNA, IP Attorneys Agent for the Applicant
Disclaimer: Curated by HT Syndication.
