Improving phoneme models for speaker-independent automatic speech recognition

This thesis explores the use of randomized, performance-based search strategies to improve the generalization of an automatic speech recognition system based on hidden Markov models. We apply simulated annealing and random search to several components of the system, including phoneme model topologies, distribution tying, and the clustering of allophonic contexts. By using knowledge of the speech problem to constrain the search appropriately, we obtain reduced numbers of parameters and higher phonemic recognition results. Performance is measured on both our own data set and the Darpa TIMIT database