摘要
过程神经网络是一种基于过程神经元的新型神经网络,其输入及权值皆为时序函数。针对语音识别的特点,对过程神经网络在语音识别技术中的应用进行了探索性的研究,并与传统的BP神经网络、径向基函数网络进行了比较。仿真结果表明,采用过程神经网络进行的语音识别,识别性能得到了提高。
Process Neural Networks（PNN）is a kind of new ANN based on Process Neuron,its inputs and weights are all functions associated with ＂time＂.Aim at the features of speech recognition,exploratory studys the application of neural network on the process in speech recognition technology,and compares with the traditional BP neural network,radial basis function networks.Experiment results show that process neural network is used in speech reccognition,recognition performance is promoted.
出处
《激光与红外》
CAS
CSCD
北大核心
2010年第10期1141-1143,共3页
Laser & Infrared
基金
黑龙江省科技攻关项目(No.2009G0085-00)资助
关键词
过程神经网络
语音识别
BP算法
process neural network
speech recognition
BP algorithm
