Create privacy-preserving, deep transfer learning based audio-visual speech enhancement algorithms.

Integrate audio-visual speech enhancement with wireless-based multi-modal models for lip-reading and cognitive load prediction.

Prototype off-chip real-time audio-visual hearing aid with low complexity, energy-efficient design.

Prototype on-chip real-time audio-visual hearing aid for 5G and beyond.

Develop a new large noisy audio-visual corpus and techniques for predicting objective speech quality/intelligibility.

Test real-time hearing aid with an environment-friendly smart care home testbed and pilot clinical evaluation.