A New Hybrid Hmm/Ann Model for Speech Recognition

Because of the application of the Hidden Markov Model (HMM) in acoustic modeling, a significant breakthrough has been made in recognizing continuous speech with a large glossary. However, some unreasonable hypotheses for acoustic modeling and the unclassified training algorithm on which the HMM based form a bottleneck, restricting the further improvement in speech recognition. The Artificial Neural Network (ANN) techniques can be adopted as an alternative modeling paradigm. By means of the weight values of the network connections, neural networks can steadily store the knowledge acquired from the training process. But they possess a weak memory, not being suitable to store the instantaneous response to various input modes. To overcome the flaws of the HMM paradigm, we design a hybrid HMM/ANN model. In this hybrid model, the nonparametric probabilistic model (a BP neural network) is used to substitute the Gauss blender to calculate the observed probability which is necessary for computing the states of the HMM model. To optimizing the network structure in and after the training process, we propose an algorithm to prune hidden nodes in a trained neural network, and utilize the generalized Hebbian algorithm to reconfigure the parameters of the network. Some experiments show that the hybrid model has a good performance in speech recognition.