Title :
Nonlinear adaptive prediction of nonstationary signals
Author :
Haykin, Simon ; Li, Liang
Author_Institution :
Commun. Res. Lab., McMaster Univ., Hamilton, Ont., Canada
fDate :
2/1/1995 12:00:00 AM
Abstract :
We describe a computationally efficient scheme for the nonlinear adaptive prediction of nonstationary signals whose generation is governed by a nonlinear dynamical mechanism. The complete predictor consists of two subsections. One performs a nonlinear mapping from the input space to an intermediate space with the aim of linearizing the input signal, and the other performs a linear mapping from the new space to the output space. The nonlinear subsection consists of a pipelined recurrent neural network (PRNN), and the linear section consists of a conventional tapped-delay-line (TDL) filter. The nonlinear adaptive predictor described is of general application. The dynamic behavior of the predictor is demonstrated for the case of a speech signal; for this application, it is shown that the nonlinear adaptive predictor outperforms the traditional linear adaptive scheme in a significant way
Keywords :
adaptive signal processing; delay circuits; delay lines; prediction theory; recurrent neural nets; speech processing; dynamic behavior; input signal; input space; intermediate space; linear mapping; linear section; nonlinear adaptive prediction; nonlinear dynamical mechanism; nonlinear mapping; nonstationary signals; output space; pipelined recurrent neural network; signal generation; speech signal; tapped delay line filter; Adaptive filters; Neural networks; Nonlinear filters; Pipeline processing; Recurrent neural networks; Signal design; Signal generators; Signal mapping; Signal processing; Speech processing;
Journal_Title :
Signal Processing, IEEE Transactions on
