This paper presents the design and implementation of a two-stage human-voice enhancement system for a hose-shaped rescue robot. When a microphoneequipped hose-shaped robot is used to search for a victim under a collapsed building, human-voice enhancement is crucial because the sound captured by a microphone array is contaminated by the ego-noise of the robot. For achieving both low latency and high quality, our system combines online and offline human-voice enhancement, providing an overview first and then details on demand. The online enhancement is used for searching for a victim in real time, while the offline one facilitates scrutiny by listening to highly enhanced human voices. Our online enhancement is based on an online robust principal component analysis, and our offline enhancement is based on an independent lowrank matrix analysis. The two enhancement methods are integrated with Robot Operating System (ROS). Experimental results showed that both the online and offline enhancement methods outperformed conventional methods.
- Blind human-voice enhancement
- Hose-shaped rescue robot
- Robot audition
- Search and rescue