45 0

A subspace approach based on embedded prewhitening for voice activity detection

Title
A subspace approach based on embedded prewhitening for voice activity detection
Author
장준혁
Keywords
Algorithms; Decision Support Techniques; Fourier Analysis, Humans; Likelihood Functions; Models; Statistical; Noise; Signal Processing; Computer-Assisted; Speech; Speech Recognition Software; Voice
Issue Date
2011-12
Publisher
Acoustical Society of America
Citation
Journal of the Acoustical Society of America, 2011, 130(5), P.EL304-EL310
Abstract
This paper presents a subspace approach for voice activity detection (VAD). The proposed approach is based on an embedded prewhitening scheme for the simultaneous diagonalization of the clean speech and noise covariance matrices to provide a decision rule based on likelihood ratio test in signal subspace domain. Experimental results show that the proposed subspace-based VAD algorithm outperforms the method using a Gaussian model in a conventional discrete Fourier transform domain at the low signal-to-noise conditions.
URI
https://asa.scitation.org/doi/10.1121/1.3638927http://hdl.handle.net/20.500.11754/65851
ISSN
0001-4966; 1520-8524
DOI
10.1121/1.3638927
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > ELECTRONIC ENGINEERING(융합전자공학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE