MUMBAI, India, July 30 -- Intellectual Property India has published a patent application (202621069633 A) filed by Sage University on June 03, 2026, for System And Method For Offline Indian Vernacular Speech Recognition.
Inventors include Dr. Prashant Jain; Ms. Sakshi Agrawal; Prof. O. P. Karada; Dr. Ati Jain; Onkar Singh; and Akash Dwivedi.
The application for the patent was published on July 24, 2026, under issue no. 30/2026.
Abstract: ABSTRACT A system (100) for offline Indian vernacular speech recognition that includes a microphone array (102) comprising two electret condenser microphones configured to receive acoustic pressure waves and generate a corresponding analog electrical signal per microphone. An audio processing circuit (104) determines cross-correlation between the analog electrical signals and generates a noise-suppressed audio signal. A speech decoding circuit (106) pre-loaded with acoustic model data and language model data for a plurality of Indian vernacular languages decodes the noise-suppressed audio signal to generate a recognized text sequence. A wireless communication interface (108) receives a remote initiation signal from a cellular device (122), generates an activation signal to switch the speech decoding circuit (106) from a standby power state to an active power state, and transmits the recognized text sequence to the cellular device (122). FIG. 1
Disclaimer: Curated by HT Syndication.
