改进的RBF神经网络非线性预测模型在语音编码中的应用

英文篇名：Application of Nonlinear Prediction Model Based on Improved RBF Neutral Network in Speech Coding System
中文刊名：飞行器测控学报
英文刊名：Journal of Spacecraft TT&C Technology
作者：孟利
英文作者：MENG Li(The 54th Research Institute of CETC ; Shijiazhuang ; Hebei Province 050081)
中文关键词：非线性预测 ; RBF ; 语音编码 ; ADPCM
英文关键词：Nonlinear Prediction ; RBF ; Speech Coding ; ADPCM
出版日期：2009-04-15
机构：中国电子科技集团公司第54研究所;
年：2009
期：02
出版单位：飞行器测控学报

摘要

用一种改进的径向基函数(RBF)神经网络建立非线性预测模型来对语音信号进行处理,在提高预测精度的同时不影响传输码率。这种改进的RBF神经网络具有计算量小,学习速度快,不易陷入局部极小等优点。将此模型应用在ADPCM语音编码系统中进行验证,其恢复的语音质量优于CCITT建议G.721中的ADPCM编码,表明该非线性预测模型具有较高的预测精度,且在语音编码系统中有着很大的实用性。
This paper uses an improved RBF neural network in establishment of a model of nonlinear prediction in order to process speech signals.As a result,the prediction accuracy is improved without any negative influence on the transmission bit rate.The improved RBF neural network features low computational complexity,fast learning capability without easily getting in local minimum.The model is validated in an ADPCM speech coding system.Test results show that the recovery of speech quality is superior to ADPCM coding in G.721 recommended by CCITT.This indicates that the model of nonlinear prediction has higher prediction accuracy and is of practical significance to speech coding systems.

引文

[1]鲍长春.低比特率数字语音编码基础[M].北京:北京工业大学出版社,2001.43-57.
    [2]Chen S,Cowan C F N,Grant P M.Orthogonal Least SquaresLearning Algorithm for Radial Basis Function Networks[J].IEEE Transactions on Neural,1991,2(2):24-25.
    [3]王炜,吴耿锋,张博锋.径向基函数(RBF)神经网络及其应用[J].中国地震,2005,(2):24-26.
    [4]魏海坤.神经网络结构设计的理论与方法[M].北京:国防工业出版社,2005.15-17.
    [5]杨行峻,迟惠生,沈平,等.语音信号数字处理[M].北京:电子工业出版社,1995.32-40.
    [6]王跃科,林嘉宇,黄芝平,等.语音信号非线性分析与处理[J].通信技术,2000,(1):61-65.
    [7]Capasso V,Serrio G.A Generalization of the Kermack-Mcken-drick Deterministic Epidemic Nodel[J].J Math Biol,1978,(42):42-43.
    [8]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005.69-75.