Generalized LRT-based voice activity detector

J. M. Górriz

doi:10.1109/LSP.2006.876340

Generalized LRT-based voice activity detector

2006-10-01

12

PRE

AI

DOI：10.1109/LSP.2006.876340

Original

Original request for help

Save

Abstract

En 中文

algorithm is proposed for improving speech recognition performance in noisy environments. The approach is based on well-known statistical tests based on the determination of the speech/non-speech bispectra by means of third-order auto-cumulants. This algorithm differs from many others in the way the decision rule is formulated being them statistical tests built on a multiple observation (MO) window consisting of averaged bispectrum coefficients of the speech signal. Clear improvements in speech/non-speech discrimination accuracy demonstrate the effectiveness of the proposed VAD. It is shown that application of a statistical detection test leads to a better separation of the speech and noise distributions, thus allowing a more effective discrimination and a tradeoff between complexity and performance. The experimental analysis carried out on the AURORA 3 databases provides an extensive performance evaluation together with an exhaustive comparison to the standard VADs, such as ITU G.729, GSM AMR, and ETSI AFE, for distributed speech recognition (DSR) and other recently reported VADs.

Keywords:

bispectra analysis

higher order statistics

noise reduction

speech/non-speech detection

Generalized LRT-based voice activity detector

Abstract

AI Summary

Journal

Organization