Paper Info
Title
Reliable likelihood ratios for statistical model-based voice activity detector with low false-alarm rate.
Abstract
The role of the statistical model-based voice activity detector (SMVAD) is to detect speech regions from input signals using the statistical models of noise and noisy speech. The decision rule of SMVAD is based on the likelihood ratio test (LRT). The LRT-based decision rule may cause detection errors because of statistical properties of noise and speech signals. In this article, we first analyze the reasons why the detection errors occur and then propose two modified decision rules using reliable likelihood ratios (LRs). We also propose an effective weighting scheme considering spectral characteristics of noise and speech signals. In the experiments proposed in this study, with almost no additional computations, the proposed methods show significant performance improvement in various noise conditions. Experimental results also show that the proposed weighting scheme provides additional performance improvement over the two proposed SMVADs.
Year
DOI
Venue
2011
10.1186/1687-6180-2011-31
EURASIP J. Adv. Sig. Proc.
Keywords
Field
DocType
voice activity detector, statistical model, reliability of likelihood ratio
Decision rule,Weighting,Likelihood-ratio test,Pattern recognition,Computer science,Speech recognition,Statistical model,Artificial intelligence,Constant false alarm rate,Detector,Performance improvement,Computation
Journal
Volume
Issue
ISSN
2011
1
1687-6180
Citations 
PageRank 
References 
6
0.37
11
Authors
3
Name
Order
Citations
PageRank
Younggwan Kim1176.11
Young-joo Suh247858.07
Hoi-Rin Kim310220.64