Skip to Main Content
A new codebook design algorithm for text-independent speaker identification based on the discrete hidden Markov model (HMM) is proposed. The optimisation criterion of the new training procedure is to make each codevector in the codebook to represent the same number of training vectors approximately rather than to minimise the quantisation error. This idea is implemented with a genetic algorithm. The new codebook is evaluated experimentally. It is shown that, for a small codebook, the speaker identification performance using the new codebook is better than that obtained using the Linde-Buzo-Grey codebook for HMM-based speaker identification.
Date of Publication: 12 May 2005