Max Robotics — Global Service Robot Directory + US Certification

About

Joon-Hyuk Chang is a leading researcher at the intersection of audio signal processing and robotics, whose work tackles the fundamental challenge of enabling machines to hear clearly amidst their own noise. His primary research areas include noise suppression, sound source localization (SSL), and robust automatic speech recognition (ASR) for motor-driven robots. Chang’s major contribution lies in developing multi-input multi-output (MIMO) noise suppression algorithms that preserve spatial cues critical for SSL, allowing mobile robots to accurately locate sounds even when their own motors generate dominant ego-noise. His most cited work, a 2021 paper on MIMO noise suppression for SSL, has garnered 11 citations for its practical approach to real-world robotic hearing. Beyond this, Chang has pioneered the integration of motor state information as auxiliary input to deep neural networks (DNNs), enabling ASR systems to adapt dynamically to changing noise conditions—a concept demonstrated in his 2018 and 2020 papers. By treating robot-generated noise not as a nuisance but as a predictable signal, Chang’s research has significantly advanced the reliability of speech interfaces for intelligent robots, paving the way for more natural human-robot interaction in noisy, dynamic environments.