We introduce a method for expressing word lattices within a dynamic graphical model. We describe a variety of choices for doing this, including a technique to relax the time information associated with lattice nodes in a way that trades off hypothesis expansion with presumed segmentation boundary accuracy. Our approach uses a set of time-inhomogeneous and algorithmically expressed conditional probability tables to encode the lattice. The approach was implemented as part of the graphical model

more »

... olkit, and word error rate improvements on the Switchboard corpus indicate that our technique is a viable means to incorporate large state space speech recognition systems into a graphical model.