Speech understanding using a unification grammar

Yen-Lu Chow, Salim Roukos

Abstract: The authors describe a system for speech understanding that uses hidden Markov models for acoustic modeling, a unification grammar for the syntax of English, and a higher order intensional logic for semantic representation. To maximize speech understanding performance, the constraints of the linguistic models must be used in the search for the most likely interpretation of the spoken message. The basic approach is to perform parsing (as in natural language processing) on the word lattice input produced by a lattice engine. The authors present two lattice parsing algorithms that determine a list (ordered by acoustic likelihood) of word sequences allowed by the grammar and present in the lattice. They describe how semantic constraints can be applied a posteriori to find the most likely interpretation of the input speech. They give speech understanding results on the standard DARPA resource management speech database.<