Anna Corazza, Renato De Mori, Roberto Gretter and Giorgio Satta
In automatic speech recognition the use of language models improves performance. Stochastic language models fit rather well the uncertainty created by the acoustic pattern matching. These models are used to score theories corresponding to partial interpretations of sentences. Algorithms have been developed to compute probabilities for theories that grow in a strictly left-to-right fashion. In this paper we consider new relations to compute probabilities of partial interpretations of sentences. We introduce theories containing a gap corresponding to an uninterpreted signal segment. Algorithms can be easily obtained from these relations. Computational complexity of these algorithms is also derived.