HRI-JP Honda Research Institute Japan (HRI-JP) – Research and development of advanced technologies

Publications > Assessment of Single-channel Ego Noise Estimation Methods

Research

publication_search

Advanced Search

September 2011

Assessment of Single-channel Ego Noise Estimation Methods

  • PDF   (639.36KB)
    Copyright (C) IEEE, 2011. The copyright of this material is retained by IEEE. This material is published on this web site by permission of IEEE for your personal use. Not for redistribution.
  • Ince_2011_864   (1.71KB)
  • G. Ince, K. Nakadai, T. Rodemann, J. Imura, K. Nakamura, H. Nakajima,
  • in Proceedings of the 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011),
  • IEEE,
  • 2011,
  • pp. 106-111,
  • Conference paper

While a robot is moving, ego noise is generated due to the fans and motors of the robot. Furthermore, a robot is not only subject to the ego noise, but also to the ambient noise of the environment, both having different shortterm signal characteristics. Because ego-motion noise generated by the motors is non-stationary, and the BackGround Noise (BGN) is stationary, one single noise estimation method is unable to track the changes in both noise spectra rapidly and accurately. Therefore, we propose to use the combination of two different noise estimation methods adequate for each one of co-existing noise types in a unified framework: 1) a stationary noise estimation method called Histogram-based Recursive Level Estimation (HRLE) and 2) a non-stationary noise estimation method called Template-based Estimation (TE). In this paper, we evaluate the performance of several singlechannel based noise estimation techniques in terms of their prediction accuracy and quality of the speech signals enhanced by spectral subtraction methods. The experimental results show that our system, compared to the conventional single-stage noise estimation methods, achieves better performance in attaining signal quality and improving word correct rates.

Search by Other Conditions

Keywords
Entry type
Years
to
Authors
Language
Refereed