Non-Linear Speech coding with MLP, RBF and Elman based prediction

TL;DR

This paper introduces a nonlinear speech predictor combining MLP, RBF, and Elman networks to enhance speech coding performance within an ADPCM scheme, demonstrating improved results over individual predictors.

Contribution

It presents a novel combined neural network predictor for speech coding and provides a comparative analysis of three neural network architectures for speech prediction.

Findings

Combined predictor improves speech coding accuracy

Neural network combination outperforms individual models

Comparative study highlights strengths of each neural network

Abstract

In this paper we propose a nonlinear scalar predictor based on a combination of Multi Layer Perceptron, Radial Basis Functions and Elman networks. This system is applied to speech coding in an ADPCM backward scheme. The combination of this predictors improves the results of one predictor alone. A comparative study of this three neural networks for speech prediction is also presented.