Dimensionality reduction methods for HMM phonetic recognition

This paper presents two nonlinear feature dimensionality reduction methods based on neural networks for a HMM-based phone recognition system. The neural networks are trained as feature classifiers to reduce feature dimensionality as well as maximize discrimination among speech features. The outputs of different network layers are used for obtaining transformed features. Moreover, the training of the neural networks uses the category information that corresponds to a state in HMMs so that the trained networks can better accommodate the temporal variability of features and obtain more discriminative features in a low dimensional space. Experimental evaluation using the TIMIT database shows that recognition accuracies with the transformed features are slightly higher than those obtained with original features and considerably higher than obtained with linear dimensionality reduction methods. The highest phone accuracy obtained with 39 phone classes and TIMIT was 74.9% using a large number of training iterations based on the state-specific targets.