隐马尔可夫模型的拓朴应用

Hidden Markov Model Topological Application

以非齐次隐马尔可夫模型(Inhomogeneous Hidden Markov Mode1)出发,用自适应函数链神经网络与非齐次隐马尔可夫模型相结合,训练出适用环境变化的HMM模型,并应用该混合模型进行语音识别.实验结果表明,该模型适合于对噪声背景下的语音进行识别,该模型具有更好的鲁棒性,在信噪比较低的情况下,可以提高识别率.

The inhomogeneous-HMM is studied,and the self-adaptive functional link neural network and an improved inhomogeneous-HMM are combined to train the HMM of adapted change.The model trained by this method is used in speech recognition experiments.Experimental results show this model has better noise robustness.In the condition of low SNR,the correct recognition rate has increased.