We developed unobtrusive silent speech interfaces using optimized materials and deep learning, enabling natural robot control and collaborative tasks for people with voice disorders and for noisy environments.
This project develops an ultrathin skin-conformable soft dry electrodes for decode EMG signals into spoken words. It performs robustly in noisy and dark environments, with applications in augmented reality and healthcare. Paper
We present a wireless, unobtrusive, and robust silent speech interface for tracking and decoding speech-relevant movements of the temporomandibular joint. Our solution employs a single soft magnetic skin placed behind the ear for wireless and socially acceptable silent speech recognition. Paper