Comparative analysis of linear and nonlinear speech signals predictors
Б А Кисельман, V.V. Krylov · IEEE Transactions on Speech and Audio Processing · 2005
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.