MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202641043263 A) filed by Dayananda Sagar College Of Engineering, Bangalore, Karnataka, on April 4, for 'system and method for wearable semg and imu-based displacement-tolerant indian sign language recognition and cross-lingual speech output.'
Inventor(s) include Prof. Pruthvi C N; Monisha R; Sufiya Sarwath; Supriya R; Yaseen Ahmed Khan; and Harpreet Kaur Thind.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "The invention provides a portable, real-time Indian Sign Language (ISL) to speech conversion system that enables seamless communication for individuals with hearing or speech impairments. The system integrates a wearable forearm band equipped with surface electromyography (sEMG) sensors and an inertial measurement unit (IMU) to capture muscular and motion signals associated with hand gestures. A low-power microcontroller ESP32 acquires and wirelessly transmits the preprocessed signals to a Transformer-based deep learning model that interprets the fused signals to recognize ISL gestures with high temporal and spatial accuracy. The recognized gestures are translated into meaningful words and sentences using a language-mapping module that adapts ISL grammar into natural spoken language. The generated text is further converted into speech in real time, with optional translation into Hindi or Kannada for wider usability. A companion mobile application manages device connectivity, displays recognized text, and plays synthesized speech, thereby providing an end-to-end communication channel. The invention offers significant advantages including portability, low latency, multilingual support, and robust gesture recognition, enabling practical day-to-day communication assistance."
Disclaimer: Curated by HT Syndication.
