An Approach to Natural Speech Understanding Based on Stochastic Models in a Hierachical Structure
Holger Stahl, Johannes Müller · 1994
In this paper, an approach for understanding natural speech by means of two stochastic knowledge bases is presented: Within a given domain, the semantic model generates possible semantic structures, which are semantic representations close to the word level. Corresponding to such a semantic structure, the syntactic model generates word chains using hierarchical Hidden-MarkovModels. Integrated into a speech understanding system, these stochastic knowledge bases can be utilized for a ’top-down’-approach.