Project Grant 2534211

The National Science Foundation Division of Computer and Network Systems awarded the University of Massachusetts $250,000 on August 15, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to design a closed-loop unvoiced interaction paradigm enabling silent communication with computing devices.

The project develops a sensor-equipped ear-worn device that detects jaw movement and facial vibrations associated with unvoiced speech, transforming these signals into words and commands without requiring audible vocalization. The system addresses limitations of conventional voice interfaces in noisy environments, privacy-sensitive public spaces, and settings where audible speech is disruptive. Research objectives include developing computational models mapping jaw kinematics and facial vibrations to phonetic and linguistic units, designing a personalized context-aware closed-loop feedback control system leveraging structured knowledge schemas for real-time adaptation, and building a low-power earable hardware platform optimized for jaw dynamics sensing with programmable computational offloading. The resulting platform will establish foundations for privacy-preserving, hands-free human-computer interaction advancing accessibility in computing systems.

Performance occurs in Amherst, Massachusetts, with a completion date of July 31, 2029. The award represents a Project Grant assistance type.