【摘要】 介绍一种适用于实时语音识别环境下的神经网络模型———动态识别神经网络(dynam ic recogn ition neu-ral network,DRNN).DRNN聚类学习的性能使得它非常适用于与在线学习方式相结合的实时语音识别系统.通过比较DRNN和隐含马尔科夫模型(h idden M arkov model,HMM),可以看到不论是在训练方面还是在识别方面,DRNN算法的计算复杂程度都要低于HMM算法.更多还原

【Abstract】 A neural network model,dynamic recognition neural network(DRNN),is presented for real-time speech recognition.The property of clustering learning of the DRNN makes it very suitable for real-time speech recognition with on-line learning ability.A comparison between the DRNN and hidden Markov model(HMM) shows that the computational complexity of the former is lower than that of the latter in both training and recognition.更多还原