A stochastic grammar for isolated representation of syntactic and semantic knowledge

Abstract

A new form of a grammar is described, which provides two separate sets of stochastic parameters for representing both the semantic and the syntactic knowledge, required for automatic speech understanding. The semantic structure is introduced as an adequate representation of natural spoken, one-sentence command utterances. The constraints and probabilities delivered by the grammar can be integrated into the framework of a stochastic top-down parser to decode the semantic content of an utterance directly from its observation sequence. The performance of the developed methods is proved for the domain of a speech understanding graphic editor, which can be controlled solely by natural spoken commands.