Paper Info
Title
On using spectral gradient in conditional MAP criterion for robust voice activity detection
Abstract
In this paper, we propose a novel approach to improve a statistical model-based voice activity detection (VAD) method based on a modified conditional maximum a posteriori (MAP) criterion incorporating the spectral gradient scheme. The proposed conditional MAP incorporates not only the voice activity decision in the previous frame as in Ref. [1] but also the spectral gradient of the observed spectra between the current frame and the past frames to efficiently exploit the inter-frame correlation of voice activity. As a result, the proposed VAD leads to six separate thresholds to be adaptively determined in the likelihood ratio test (LRT) depending on both the previous VAD result and the estimated spectral gradient parameter. Experimental results demonstrate that the proposed approach yields better results compared to those of the previous conditional MAP-based method.
Year
DOI
Venue
2012
10.1109/ICNIDC.2012.6418777
"IC-NIDC
Keywords
Field
DocType
maximum likelihood estimation,speech recognition,map criterion,vad method,conditional map-based method,conditional map criterion,estimated spectral gradient parameter,inter-frame correlation,likelihood ratio test,modified conditional maximum a posteriori,robust voice activity detection,spectral gradient,spectral gradient scheme,statistical model-based voice activity detection,conditional map,voice activity detection
Pattern recognition,Likelihood-ratio test,Voice activity detection,Maximum likelihood,Correlation,Statistical model,Artificial intelligence,Maximum a posteriori estimation,Mathematics
Conference
ISBN
Citations 
PageRank 
978-1-4673-2201-0
0
0.34
References 
Authors
7
2
Name
Order
Citations
PageRank
Jae-Hun Choi1295.57
joonhyuk213626.87