摘要
给出一种改进的具有四层网络结构的T-S模糊神经网络算法,通过在隶属度上加入一个与输入维数有关的补偿因子,使其能够应用到语音识别系统中,并解决了由输入维数过大而引起的规则灾问题。实验结果表明改进的T-S模糊神经网络能够应用于语音识别系统,同时表明该网络的识别率比RBF网络高,并且鲁棒性较好。
An improved T-S fuzzy neural network with four layers network structure is introduced.This algorithm adds a compen-sated factor interrelated with the input dimensions on the membership degree,which can be applied into the speech identification system.In the meanwhile it also solves the ＂regulation disaster＂problems caused by the intensive input dimensions.The experi-ment results show the improved T-S fuzzy neural network is applied to speech recognition system,and the recognition ratio of this network is higher than RBF network,meanwhile obtains much better robustness.
出处
《计算机工程与应用》
CSCD
北大核心
2009年第4期246-248,共3页
Computer Engineering and Applications
基金
国家自然科学基金No.60472094
山西省自然科学基金No.20051039~~
关键词
模糊
神经网络
语音识别
fuzzy
neural network
speech recognition
