5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Unsupervised Training of HMMs With Variable Number of Mixture Components Per State

Cesar Martin del Alamo (1), Luis Villarrubia (1), Francisco Javier Gonzalez (2), Luis A. Hernandez (2)

(1) Telefonica I+D, Spain
(2) ETSI Telecomunicación, Spain

In this work automatic methods for determining the number of gaussians per state in a set of Hidden Markov Models are studied. Four different mix-up criteria are proposed to decide how to increase the size of the states. These criteria, derived from Maximum Likelihood scores, are focused to increase the discrimination between states obtaining different number of gaussians per state. We compare these proposed methods with the common approach where the number of density functions used in every state is equal and pre-fixed by the designer. Experimental results demonstrate that performance can be maintained while reducing the total number of density functions by 17% (from 2046 down to 1705). These results are obtained in a flexible large vocabulary isolated word recognizer using context dependent models.

Full Paper

Bibliographic reference.  Martin del Alamo, Cesar / Villarrubia, Luis / Gonzalez, Francisco Javier / Hernandez, Luis A. (1998): "Unsupervised training of HMMs with variable number of mixture components per state", In ICSLP-1998, paper 0443.