MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202641082880 A) filed by Brindha S on July 06, 2026, for Ai-Powered Silent Speech Reconstruction System Using Multi-Modal Bio Signal Fusion And Digital Voice Twin Technology.
Inventors include Brindha S; Sountharia I N; Rajeshwari T; Sri Darshan S B; Jyothiprabha V K; Sumith P; Prerana N M; Kanishk Sa; and Tamizh Selvan S.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: ABSTRACT: The present invention discloses a wearable, non-invasive, edge-AI-powered system and corresponding method for the real-time reconstruction of silent speech and restoration of a user's personalized synthesized voice. The system simultaneously acquires three physiological signal modalities from the user's face and cervical anatomy during silent speech production: (i) surface electromyographic (sEMG) signals from perioral, submental, and sternocleidomastoid muscle groups via Ag/AgCl dry-contact electrodes interfaced to an ADS1299 24-bit analog front-end; (ii) sub-audible laryngeal wall vibration signals via a piezoelectric contact microphone affixed at the thyroid cartilage; and (iii) articulatory kinematic signals comprising jaw displacement, lip movement, and head orientation captured by an MPU-6050 six-axis inertial measurement unit. All three signal streams are digitized at 24-bit resolution, hardware-timestamped for cross-channel temporal alignment, and subjected to real-time digital preprocessing
Disclaimer: Curated by HT Syndication.
