Design of the Nonlinear Prediction Model for Chinese Speech Signal Based on RBF Neural Network

DOI

10.2991/meees-18.2018.41How to use a DOI?

Keywords

Nonlinear prediction model, Chinese speech signal, Radical Basis Function Neural Network

Abstract

The nonlinear characteristic of Chinese speech signal are further studied, combined with radical basis function neural network, a nonlinear prediction model is designed. Firstly, delay time, embed dimension and maximum lyapunov exponent of Chinese speech phoneme are calculated by using C-C algorithm, false neatest neighbor algorithm and wolf algorithm, it is found out that Chinese speech signal has nonlinear characteristic. Secondly, combined with delay time and embed dimension, radical basis function neural network analysis method is applied successfully to design nonlinear prediction model. Lastly, compared with adaptive differential pulse code modulation linear prediction model and back propagation neural network nonlinear prediction model, prediction error of the nonlinear prediction model is significantly reduced, and the prediction performance gets much better.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xiaohong Gao
PY  - 2018/05
DA  - 2018/05
TI  - Design of the Nonlinear Prediction Model for Chinese Speech Signal Based on RBF Neural Network
BT  - Proceedings of the 2018 International Conference on Mechanical, Electrical, Electronic Engineering & Science (MEEES 2018)
PB  - Atlantis Press
SP  - 232
EP  - 239
SN  - 2352-5401
UR  - https://doi.org/10.2991/meees-18.2018.41
DO  - 10.2991/meees-18.2018.41
ID  - Gao2018/05
ER  -