## Interspeech'2005 - Eurospeech## Lisbon, Portugal |

Nowadays, HMM-based speech recognition systems are used in many real time processing applications, from cell phones to automobile automation. In this context, one important aspect to be considered is the HMM model size, which directly determines the computational load. So, in order to make the system practical, it is interesting to optimize the HMM model size constrained to a minimum acceptable recognition performance. Furthermore, topology optimization is also important for reliable parameter estimation. Previous works in this area have used likelihood measures in order to obtain models with a better compromise between acoustic resolution and robustness. This work presents a new approach based on a Gaussian Importance Measure (GIM) used in the Gaussian Elimination Algorithm (GEA) for determining the more suitable HMM complexity. The results are compared to the classical Bayesian Information Criterion.

__Bibliographic reference.__
Yared, Glauco F. G. / Violaro, Fábio / Sousa, Lívio C. (2005):
"Gaussian elimination algorithm for HMM complexity reduction in continuous speech recognition systems",
In *INTERSPEECH-2005*, 377-380.