摘要
针对目前在噪音环境下语音识别系统性能较差的问题,利用RBF神经网络具有最佳逼近性能、训练速度快等特性,分别采用聚类和全监督训练算法,实现了基于RBF神经网络的抗噪语音识别系统。聚类算法的隐含层训练采用K-均值聚类算法,输出层的学习采用线性最小二乘法;全监督算法中所有参数的调整基于梯度下降法,它是一种有监督学习算法,能够选出性能优良的参数。实验表明,在不同的信噪比下,全监督算法较之聚类算法有更高的识别率。
To solve the problem that recognition rates of speech recognition systems decrease in the noisy environment presently, uses character possessing RBF neural network,which have optimal approach capability and the fast training speed,adopts clustering algorithm and whole supervision algorithm and realizes a noise-robust speech recognition system based on RBF neural network.The hidden layer training of clustering algorithm used K-means clustering algorithm and output layer learning used linear least mean square.The adjustment of the entire parameters of whole supervision algorithm is based on grads decline method.It is a kind of supervised learning algorithm and can choose excellent parameters.Experiments show that whole supervision algorithm have higher recognition rates in different SNRs than clustering algorithm.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第22期28-30,共3页
Computer Engineering and Applications
基金
国家自然科学基金(the National Natural Science Foundation of China under Grant No.60472094)
山西省自然科学基金(the Natural Science Foundation of Shanxi Province of China under Grant No.20051039)。
关键词
语音识别
RBF神经网络
聚类算法
全监督算法
speech recognition
RBF neural network
clustering algorithm
whole supervision algorithm
