In this paper, a first version of a system for statistical translation and present experimental results is described. The statistical translation approach uses two types of information: a translation model and a language model. The language model used is a standard bi-gram model. The translation model is decomposed into lexical and alignment models. After presenting the details of the alignment model, the authors describe the search problem and present a dynamic programming-based solution for the special case of monotone alignments. So far, the system has been tested on two limited-domain tasks for which a bilingual corpus is available: the EuTrans traveller task (Spanish–English, 500-word vocabulary) and the Verbmobil task (German–English, 3000-word vocabulary). The authors present experimental results on these tasks. In addition to the translation of text input, they also address the problem of speech translation and suitable integration of the acoustic recognition process and the translation process.