Nonlinear prediction for speech coding using radial basis functions

Author

Díaz-de-María, Fernando ; Figueiras-Vidal, Anibal R.

Author_Institution

Dept. de Electron., Cantabria Univ., Santander, Spain

Volume

1

fYear

1995

fDate

9-12 May 1995

Firstpage

788

Abstract

Radial basis functions (RBF) networks constitute an interesting option for dealing with nonlinear prediction of speech because they provide a regularized solution. They can guarantee the stability of the corresponding synthesis scheme; consequently, they are used in code excited nonlinear prediction (CENP) coders. This approach is presented, and some simulations examples show its advantage in the prediction performance. The practical implementations of CENP coders are also addressed

Keywords

feedforward neural nets; multilayer perceptrons; prediction theory; speech coding; speech processing; speech synthesis; vocoders; CENP coders; code excited nonlinear prediction coders; nonlinear prediction; prediction performance; radial basis functions networks; regularized solution; simulations examples; stability; synthesis scheme; Human voice; Network synthesis; Predictive coding; Predictive models; Quantization; Signal mapping; Speech coding; Speech synthesis; Stability; Switches; Telecommunications;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on

Conference_Location

Detroit, MI

ISSN

1520-6149

Print_ISBN

0-7803-2431-5

Type

conf

DOI

10.1109/ICASSP.1995.479812

Filename

479812