Label	95kai
Title	Training of the Semantic Model for a Speech Understanding Graphic Editor
Authors	Janez Kaiser, Johannes Müller, Holger Stahl
Type	Scientific Conference Paper
Abstract	In this paper, an algorithm for the training of the semantic model and the addition of floor values into the semantic model for a speech controlled graphic editor is presented. The speech understanding module of the graphic editor uses a grammar, consisting of two stochastic knowledge bases: the semantic model and the syntactic model. Within a 'top-down' strategy, the semantic model generates semantic structures, which are semantic representations close to the word level, with the respective probabilities.
Reference	Proceedings ERK'95 - 4th Conference on Electronics and Computer Science (Portoroz, Slovenia, 1995), Section IEEE, vol. B, pp. 285-288
Published	September 1995
Language	English
Download	Scientific Conference Paper as pdf file  (34 kByte)