Gang Ji, Jeff Bilmes, Jeff Michels, Katrin Kirchhoff, Chris Manning
2006 2006 IEEE Spoken Language Technology Workshop  
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.
doi:10.1109/slt.2006.326842 dblp:conf/slt/JiBKM06 fatcat:tyyi57vfn5dv5iqbfhp7emrx3e