Chin‐Hui Lee

Papers

Total Citations

110

H-Index

About

Chin-Hui Lee is a pioneering figure in the fields of automatic speech processing, deep reinforcement learning, and adversarial machine learning. His work bridges foundational signal processing with cutting-edge neural network architectures, most notably through his influential paper “An Artificial Neural Network Approach to Automatic Speech Processing” (2014, 85 citations), which helped catalyze the shift from traditional hidden Markov models to deep learning frameworks for speech recognition. Lee’s research also extends into the security of intelligent systems, as demonstrated by his study “Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning” (2020, 25 citations), which exposed critical vulnerabilities in DRL-based autonomous navigation and robotic control. By revealing how strategically timed perturbations can undermine self-adaptive learning systems, Lee has made essential contributions to robust AI design. His work is widely cited for its practical impact on both speech technology and safe reinforcement learning, earning him recognition as a leading voice in the intersection of adaptive machine learning and real-world deployment. For students and researchers, Lee’s career exemplifies how deep technical insight into neural adaptation can drive innovation across speech, robotics, and security.