Title :
A new algorithm for end-point detection based on fourth-order cumulants
Author :
Chen, Ke ; Wang, Zengfu
Author_Institution :
Dept. of Autom., Univ. of Sci. & Technol. of China, China
fDate :
27 June-3 July 2005
Abstract :
A new algorithm for end-point detection in noisy background conditions based on the statistical properties of higher-order cumulants of speech signal is presented in this paper. Since the higher-order cumulants are blind for Gaussian signal, the proposed method is especially effective to the problem of end-point detection of speech signals in Gaussian noise. The above conclusions are supported by the experimental results.
Keywords :
Gaussian noise; higher order statistics; noise; speech processing; Gaussian noise; Gaussian signal; end-point detection; fourth-order cumulants; higher-order cumulants; noisy background condition; speech signal; Acoustic noise; Automation; Detection algorithms; Face detection; Gaussian noise; Random processes; Random variables; Signal to noise ratio; Speech enhancement; Speech recognition;
Conference_Titel :
Information Acquisition, 2005 IEEE International Conference on
Print_ISBN :
0-7803-9303-1
DOI :
10.1109/ICIA.2005.1635135
