基于小波混沌神经网络的语音识别

Speech recognition based on wavelet chaotic neural network

基于语音信号的时变特性,提出了一种新型神经网络语音识别方法——小波混沌神经网络方法,即把小波变换和混沌特性引入到神经元,构成小波混沌神经网络,将这种神经网络用于语音识别,并与常用的BP神经网络识别方法进行了比较。实验结果表明,小波混沌神经网络的平均识别率要高于同等条件下常用的神经网络方法的识别率。

This paper proposed a new speech recognition method of neural network, introduced wavelet transform and chaotic characteristic to neurons, and built a wavelet chaotic neural network（WCNN）. It applyed the class of neural network to speech recognition and compared the performance of the network with BP neural network, The experimental results show that chaotic neural network method outperforms the BP method.