Title :
On Second-Order Statistics of Log-Periodogram With Correlated Components
Author :
Ephraim, Yariv ; Roberts, William J.J.
Author_Institution :
Dept. of Electr. & Comput. Eng., George Mason Univ., Fairfax, VA, USA
Abstract :
We derive an explicit expression for the covariance of the log-periodogram power spectral density estimator for a zero mean Gaussian process. We do not make the assumption that the spectral components of the process are uncorrelated. Applications to spectral estimation and to cepstral modeling in automatic speech recognition are discussed.
Keywords :
Gaussian processes; cepstral analysis; correlation methods; covariance analysis; speech recognition; automatic speech recognition; cepstral modeling; correlated components; covariance; log-periodogram power spectral density estimator; second-order statistics; zero mean Gaussian process; Additive noise; Autocorrelation; Automatic speech recognition; Cepstral analysis; Discrete Fourier transforms; Frequency; Gaussian processes; Silver; Speech recognition; Statistics; Log-periodogram; speech recognition;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2005.853049
