Robust Voice Activity Detection at Noisy Environment Using Average Estimate Least Mean Square Filter

Author

Sang-Yeob Oh ; Chan-Shik Ahn

Author_Institution

Dept. of Interactive media, Gachon Univ., Seongnam, South Korea

fYear

2013

fDate

24-26 June 2013

Firstpage

1

Lastpage

2

Abstract

In this paper, noise gets reduced with an average estimate LMS filter in a car noise environment so robust voice activities are being detected in a car noise environment. For the noise reduction, an average estimate LMS filter, which is a method for maintaining a source feature of speech and decreasing damages on speech information, is used in a speech signal detection process to reduce noise from a polluted speech signal. An average estimator was calculated and a step size of a LMS filter was controlled with a frame measure to improve an adaptation speed. Moreover, the starting point of result speech, comparing to the previous method of using frame energy was found to be improved by 1.7% and 3.7% of an error rate and an end point error rate, respectively.

Keywords

acoustic signal detection; filtering theory; least mean squares methods; signal denoising; speech processing; LMS filter step size control; adaptation speed improvement; average estimate LMS filter; average estimate least mean square filter; car noise environment; end point error rate; frame measure; noise reduction; noisy environment; polluted speech signal; robust voice activity detection; speech information; speech signal detection process; speech source feature; Finite impulse response filters; Information filtering; Least squares approximations; Noise; Robustness; Speech; Speech processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Science and Applications (ICISA), 2013 International Conference on

Conference_Location

Suwon

Print_ISBN

978-1-4799-0602-4

Type

conf

DOI

10.1109/ICISA.2013.6579394

Filename

6579394