Ego noise cancellation of a robot using missing feature masks


Ince G., NAKADAI K., RODEMANN T., TSUJINO H., IMURA J.

APPLIED INTELLIGENCE, vol.34, no.3, pp.360-371, 2011 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 34 Issue: 3
  • Publication Date: 2011
  • Doi Number: 10.1007/s10489-011-0285-0
  • Journal Name: APPLIED INTELLIGENCE
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.360-371
  • Istanbul Technical University Affiliated: No

Abstract

We describe an architecture that gives a robot the capability to recognize speech by cancelling ego noise, 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 separation and post-filtering; (2) a single-channel noise reduction block utilizing template subtraction; and (3) an automatic speech recognition block. In this work, we specifically investigate a missing feature theory-based automatic speech recognition (MFT-ASR) approach in block (3). This approach makes use of spectro-temporal elements derived from (1) and (2) to measure the reliability of the acoustic features, and generates masks to filter unreliable acoustic features. We then evaluated this system on a robot using word correct rates. Furthermore, we present a detailed analysis of recognition accuracy to determine optimal parameters. Implementation of the proposed MFT-ASR approach resulted in significantly higher recognition performance than single or multi-channel noise reduction methods.