A STUDY ON SPEAKER ADAPTATION FOR MANDARINE SYLLABLE RECOGNITION WITH MINIMUM ERROR DISCRIMINATIVE TRAINING

This paper investigates a different method of speaker adaptation for Mandarin syllable recognition. Based on the minimum classification error (MCE) criterion, we use the generalized probabilistic decent (GPD) algorithm to adjust iteratively the parameters of the hidden Markov models (HMM). The experiments on the multi-speaker Mandarin syllable database of Telecommunication Laboratories (T.L.) yield the following results: 1) Efficient speaker adaptation can be achieved through discriminative training using the MCE criterion and the GPD algorithm. 2) The computations required can be reduced through the use of the confusion sets in Mandarin base syllables. 3) For the discriminative training, the adjustment on the mean values of the Gaussian mixtures has the most prominent effect on speaker adaptation. 4) The discriminative training approach can be used to enhance the speaker adaptation capability of the maximum a posteriori (MAP) approach.