Stochastic finite-state models are efficiently learnable from data, effective for decoding and are associated with a calculus for composing models which allows for tight integration of constraints frora various levels of language processing. In this paper, we present a method for stochastic finite-state machine translation that is trained automaticMly from pairs of source and target utterances. We use this method to develop models for English-Japanese and Japanese-English translation. We have embedded the Japanese-English translation system in a call routing task of unconstrained speech utterances. We evaluate the efficacy of the translation system .in the context of this application.