JACIII Vol.4 No.1 pp. 120-127
doi: 10.20965/jaciii.2000.p0120


A New Approach To Speech Coding: the Neural Predictive Coding

Bruno Gas, Jean Luc Zarader and Cyril Chavy

Laboratoire des Instruments et Systemes, Universite Paris VI 4 place Jussieu, 75252 Paris cedex 05, France

June 23, 1999
November 10, 2000
January 20, 2000
Speech signal coding, Neural networks, Non linear predictive coding, Phonemes recognition, Discriminant feature extraction (DFE)

In this article we propose a new speech signal coding model applied to the recognition of phonemes. This model is an extension to the non linear area of adaptive coding systems used in speech processing. For this purpose, we use predictive connectionist methods. We show that it is possible to take into account class membership information of the phonemes from the stage of coding. To evaluate the NPC encoder, a study of a database of phonemes by discriminant analysis and an application to phonemes recognition are carried out. Simulations presented here show that classification has obviously been improved, compared to currently used types of coding.

Cite this article as:
Bruno Gas, Jean Luc Zarader, and Cyril Chavy, “A New Approach To Speech Coding: the Neural Predictive Coding,” J. Adv. Comput. Intell. Intell. Inform., Vol.4, No.1, pp. 120-127, 2000.
Data files:

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Mar. 05, 2021