We describe techniques for enhancing the accuracy, efficiency and features of a low-resource, medium-vocabulary, grammar-based speech recognition system, which uses hidden Markov models. Among the issues and techniques we explore are reducing computation via silence detection, applying the Bayesian information criterion (BIC) to build smaller and better acoustic models, minimizing finite state grammars, using hybrid maximum likelihood and discriminative models, and automatically generating baseforms from single new-word utterances. We report WER figures where appropriate.