Humanoid robot noise suppression by particle filters for improved automatic speech recognition accuracy

Automatic speech recognition on a humanoid robot is exposed to numerous known noises produced by the robot’s own motion system and background noises such as fans. Those noises interfere with target speech by an unknown transfer function at high distortion levels, since some noise sources might be closer to the robot’s microphones than the target speech sources. In this paper we show how to remedy those distortions by a speech feature enhancement technique based on the recently proposed particle filters. A significant increase of recognition accuracy could be reached at different distances for both engine and background noises.