Semantics in speech recognition and understanding: a survey
Eric Atwell, George Demetriou · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · 1994
This survey paper aims at summarizing the state of the art of computational semantic methods in speech recognition and understanding research. A taxonomy classifying the approaches adopted in the literature is divided into six main categories: semantic networks, semantic grammars, caseframes, statistical, unification-based and neural networks. For each approach, an overview of the variety of uses and relative strengths and weaknesses is given.