Paper Info
Title
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 context- dependent 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.
Year
Venue
Keywords
2002
INTERSPEECH
continuous hmms,large vocabulary recognition,agglomerative clustering.,telephone- based,context dependent,word recognition
Field
DocType
Citations 
Hierarchical clustering,Recognition system,Pattern recognition,Computer science,Speech recognition,Gaussian,Artificial intelligence,Context independent,Cluster analysis,Hidden Markov model,Vocabulary,Directory assistance
Conference
2
PageRank 
References 
Authors
0.47
6
5
Name
Order
Citations
PageRank
Ricardo De Córdoba114225.58
Javier Macías Guarasa213825.19
Javier Ferreiros320.47
Juan Manuel Montero421831.51
José Manuel Pardo515230.36