Discriminative training of GMM-HMM acoustic model by RPCL type Bayesian Ying-Yang harmony learning

This paper presents a new discriminative approach for training Gaussian mixture models (GMMs) of hidden Markov models (HMMs) based acoustic model in a large vocabulary continuous speech recognition (LVCSR) system. This approach is featured by embedding a rival penalized competitive learning (RPCL) mechanism on the level of hidden Markov states. For every input, the correct identity state, called winner , is enhanced to describe this input while its most competitive rival is penalized by de-learning, which makes GMMs based states become more discriminative. Experiments show that the proposed method has a good convergence with better performances than the classical MLE based method. Comparing with three conventional discriminative methods, the proposed method demonstrates improved generalization ability, especially when the test set is not well matched with the training set.