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 Córdoba | 1 | 142 | 25.58 |
Javier Macías Guarasa | 2 | 138 | 25.19 |
Javier Ferreiros | 3 | 2 | 0.47 |
Juan Manuel Montero | 4 | 218 | 31.51 |
José Manuel Pardo | 5 | 152 | 30.36 |