We present in this paper a statistical model for language-independent bi-directional conversion between spelling and pronunciation, based on joint grapheme/phoneme units extracted from automatically aligned data. The model is evaluated on spelling-to-pronunciation and pronunciation-to-spelling conversion on the NetTalk database and the CMU dictionary. We also study the effect of including lexical stress in the pronunciation. Although a direct comparison is difficult to make, our model's performance appears to be as good or better than that of other data-driven approaches that have been applied to the same tasks.