The primary problem in large vocabulary conversational speech recognition (LVCSR) is poor acoustic-level matching due to large variability in pronunciations. There is much to explore about the "quality" of states in an HMM and the inter-relationships between inter-state and intra-state Gaussians used to model speech. Of particular interest is the variable discriminating power of the individual states and its relation to the initial model topology. In this project we exploit such dependencies through model topology optimization based on the Bayesian Information Criterion (BIC).