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.

Decision trees havebeen used in speech recognition with large numbers of context-dependentHMM models, to provide models for contexts not seen in training. Trees are usually created by successive node splitting decisions, based on how well a single Gaussian or Poisson density fits the data associated with a node. We introduce a new node splitting criterion, derived from the maximum likelihood fitting of the complex node distributions with Gaussian tiedmixture densities. We also carry the use of decision trees for tying HMM models a step further. In addition to questions about phonetic class of neighbouring phonemes,we allow questions about the HMM model state to be asked. The resulting decision tree maximizes the likelihood by adjusting the amount of parameter tying simultaneously across state and context. Accuracy improvement and model size reduction were evaluated on a gender-dependent 5K closed-vocabulary WSJ task, using the SI-84 and SI-284 training sets, for tied-mixture and continuous HMMmodels. The new decision trees are shown to reduce both error rate and model size, while being computationally cheap enough to allow consideration of two preceding and two following phones for the context.