独立ベクトル分析とノイズキャンセラを用いた雑音抑圧の柔軟索状ロボットへの適用

抄録

This paper presents a noise reduction on a hose-shaped rescue robot. The hose-shaped rescue robot is one of rescue robots developed on Tough Robotics Challenge, and it is used for searching for victims by getting one’s voice with its microphone-array. However, the ego noise, caused by its vibration motors, makes it difficult to get the human voice. We propose a noise reduction method using a blind source separation technique based on Independent Vector Analysis (IVA) and noise cancellation. Our method consists of two steps: (1) estimating a speech signal and an ego-noise signal from observed multi-channel signals using the IVA-based blind source separation technique, and (2) applying the noise cancellation to the estimated speech signal using the estimated ego-noise signal as a noise reference.