SS-05: Silent Speech Recognition with Facial Electromyographic Signals using Deep Learning Algorithms
Session Organizers
This proposal aims to develop a silent speech interface (SSI) system and its key components for signal sensing and processing. The proposed system employs artificial intelligence techniques for enabling oral communication by decoding speech from non-acoustic biosignals generated during human speech activities. SSIs offer an alternative new scheme of restoring oral communication capabilities for speech-impaired people. The proposed interface allows users to silently converse using a wearable sensing device without producing any voice.
- Prof. Yao-Joe Yang, National Taiwan University, Taiwan
- Prof. Wen-Cheng Kuo, National Kaohsiung University of Science and Technology, Taiwan
This proposal aims to develop a silent speech interface (SSI) system and its key components for signal sensing and processing. The proposed system employs artificial intelligence techniques for enabling oral communication by decoding speech from non-acoustic biosignals generated during human speech activities. SSIs offer an alternative new scheme of restoring oral communication capabilities for speech-impaired people. The proposed interface allows users to silently converse using a wearable sensing device without producing any voice.
