Gökhan Ince, Kazuhiro Nakadai, Tobias Rodemann, Hiroshi Tsujino, Jun-ichi Imura, "Robust Ego Noise Suppression of a Robot", 2010.

This paper describes an architecture that can enhance a robot with the capability of performing automatic speech recognition even while the robot is moving. The system consists of three blocks: (1) a multi-channel noise reduction block comprising consequent stages of microphone-array-based sound localization, geometric source separa- tion and post filtering, (2) a single-channel template subtraction block and (3) a speech recognition block. In this work, we specifically investi- gate a missing feature theory based automatic speech recognition (MFT- ASR) approach in block (3), that makes use of spectrotemporal elements that are derived from (1) and (2) to measure the reliability of the au- dio features and to generate masks that filter unreliable speech features. We evaluate the proposed technique on a robot using word error rates. Furthermore, we present a detailed analysis of recognition accuracy to determine optimal parameters. Proposed MFT-ASR implementation at- tains significantly higher recognition performance compared to the per- formances of both single and multi-channel noise reduction methods.