Improvement of speech recognition for robots using blind signal separation

Abstract

For modern entertainment and service robots, it is desirable to establish good verbal communication with humans. This communication may easily be influenced or even completely suppressed by noise. An often neglected source of noise is that produced by the robot motors. In this paper we will show how to extract the motor noise of a robot, separate it from the desired input, and how to improve the robustness of speech recognition using Blind Source Separation.

@inproceedings{Bicher2008,
 author = {Bicher, Daniel and Kroll-Peters, Olaf and Lee, Thebin and Tiotuico, Natascha and Wilhelm, Mathias},
 title = {Improvement of speech recognition for robots using blind signal separation},
 booktitle = {Proceedings of the 8th conference on Signal processing, computational geometry and artificial vision},
 year = {2008},
 isbn = {978-960-6766-95-4},
 location = {Rhodes, Greece},
 pages = {52--55},
 numpages = {4},
 url = {http://portal.acm.org/citation.cfm?id=1503734.1503743},
 acmid = {1503743},
 publisher = {World Scientific and Engineering Academy and Society (WSEAS)},
 address = {Stevens Point, Wisconsin, USA},
 keywords = {Aibo, blind signal separation, robotics, speech recognition},
}

Authors:

Daniel Bicher, Olaf Kroll-Peters, Thebin Lee, Natascha Jasmin Tiotuico, Mathias Wilhelm

Category:

Conference Paper

Year:

2008

Location:

Proceedings of the 8th conference on Signal processing, computational geometry and artificial vision.