Graphical model representations of word lattices

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 toolkit, 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.