By Topic

GLS-based TV-CAR speech analysis using forward and backward linear prediction

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Funaki, K. ; Comput. & Networking Center, Ryukyus Univ., Okinawa, Japan

We have already proposed novel robust parameter estimation algorithms of a time-varying complex AR (TV-CAR) model for analytic speech signals, which are based on GLS (generalized least squares) and ELS (extended least squares) and have shown that the methods can achieve robust speech spectrum estimation against additive white Gaussian. In these methods, forward prediction error is only used to calculate the MSE criterion. This paper proposes the improved TV-CAR speech analysis methods based on forward and backward linear prediction in which backward prediction error is also adopted to calculate the MSE criterion, viz., the MMSE and GLS-based algorithms using the forward and backward prediction. The experiments with natural speech and natural speech corrupted by white Gaussian demonstrate that the improved methods can achieve more accurate and more stable spectral estimation.

Published in:

Multimedia Signal Processing, 2002 IEEE Workshop on

Date of Conference:

9-11 Dec. 2002