• A porous pyramid-structured triboelectric nanogenerator sensor is designed for self-powered silent speech signal acquisition.
• A hybrid neural network combining CNN and LSTM accurately decodes silent speech signals with 95.83% accuracy across 30 word categories.
• Silent speech commands enable real-time, contactless control of smartphones and immersive AR/VR interaction.
• The system offers a novel human-machine interaction approach with high sensitivity in low-force pressure detection.
Download Full PDF: TENG-Based Self-Powered Silent Speech Recognition Interface: from Assistive Communication to Immersive AR/VR Interaction | SinoTechIntel | SinoTechIntel