Title :
Comparative analysis of linear and nonlinear speech signals predictors
Author :
Kiselman, Broneslav A. ; Krylov, Vladimir V.
Author_Institution :
Nijny Novgorod State Tech. Univ., Russia
Abstract :
The paper presents a new approach to speech production modeling based on nonlinear predictors of signals. The coefficients of latter are found by solving the system of linear algebraic equations with use of least squares method. The comparative experiments were carried out to demonstrate the absolute superiority of nonlinear models over linear one in terms of normalized mean-square error.
Keywords :
discrete time systems; least mean squares methods; linear algebra; linear systems; prediction theory; signal processing; speech processing; discrete time system; least squares method; linear algebraic equation; linear speech signal; nonlinear predictors signal; normalized mean-square error; speech production modeling; Additives; Discrete time systems; Least squares methods; Neural networks; Nonlinear equations; Predictive models; Signal analysis; Signal synthesis; Speech analysis; Speech synthesis; Discrete time systems; nonlinear systems; prediction methods; speech processing; system modeling;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
DOI :
10.1109/TSA.2005.853007
