ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article Efficient Spectrum Estimation of Noise using Line Spectral Pairs for Robust Speech Recognition
Cited 8 time in scopus Share share facebook twitter linkedin kakaostory
Authors
G.-J. Jang, H.-Y. Cho
Issue Date
2011-12
Citation
Electronics Letters, v.47, no.25, pp.1399-1401
ISSN
0013-5194
Publisher
IET
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.1049/el.2011.2830
Abstract
A novel method for estimating the power spectral density of acoustic background noise is proposed. The spectral peak frequencies are approximated by the roots of the P polynomial, which constitute half of the line spectral pairs. The probability distributions of the magnitude values at the spectral peaks are modelled by a mixture of two univariate Gaussian functions, where the Gaussian with smaller mean is considered as noise and the other as speech. The validity of the proposed method is exhibited by the experimental results evaluated on a simple speech recognition task. © 2011 The Institution of Engineering and Technology.
KSP Keywords
Background noise, Estimation of noise, Gaussian functions, Line spectral pairs, Probability distribution, Robust Speech Recognition, Spectral peaks, novel method, power spectral density(PSD), spectrum estimation