State clustering improvements for continuous HMMs in a Spanish large vocabulary recognition system

Abstract

In this paper we present a whole set of improvements that have been applied to a large vocabulary isolated-word recognition system using continuous models. This system has been used in the EU funded IDAS project (LE4-8315), where an automated interactive telephone-based directory assistance service has been developed.We cover both improvements in the techniques for continuous HMM reestimation and agglomerative clustering for contextdependent models, all of them applied to our database in Spanish. Specifically, we will show how a new distance between states can greatly improve the performance of the clustering process. We show a new strategy for the clustering itself based in multiple Gaussian clustering which improved the results too. And finally, we present a new way to find the optimum number of Gaussians for each state that can be applied to both context dependent and context independent models.