Abstract
Expectation-based speech recognition is a knowledge-based approach to recognize continously spoken German speech. The knowledge base mainly consists of a large comprehensive lexicon providing various informations about each word of the registered vocabulary. During the recognition process numerous weighted hypotheses are generated that enter into competition with each other. To succeed in recognition the task is to keep the number of alternative hypotheses low by making good choices among all alternatives. The S*-algorithm performs an optimal search strategy regarding phrase hypotheses and using the information given by categorial search trees.
This work was supported by the Deutsche Forschungsgemeinschaft (DFG)
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
ERMAN, L.D., LESSER, V.R.: The HEARSAY-II Speech Understanding System: A Tutorial. In: Lea, W.A. (ed.): Trends in Speech Recognition. Prentice-Hall, Englewood Cliffs, 1980
MUDLER, J.: A System For Improving The Recognition Of Fluently Spoken German Speech. Proc. IJCAI-83, pp. 633–635
MUDLER, J., PAULUS, E.: Entwicklung und Erprobung der erwartungs- orientierten Analyse für die automatische Spracherkennung. Sprache und Datenverarbeitung, 8. Jahrgang, 1984, Heft 1/2, S. 64–71.
MUDLER, J.: Erwartungsorientierte Spracherkennung. Dissertation, Technische Universität Braunschweig, 1987
RUSKE, G.: Halbsilben als Verarbeitungseinheiten bei der automatischen Spracherkennung. Sprache und Datenverarbeitung, 8. Jahrgang, 1984, Heft 1/2, S. 5–16
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1988 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mudler, J., Paulus, E. (1988). Expectation-Based Speech Recognition. In: Niemann, H., Lang, M., Sagerer, G. (eds) Recent Advances in Speech Understanding and Dialog Systems. NATO ASI Series, vol 46. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-83476-9_43
Download citation
DOI: https://doi.org/10.1007/978-3-642-83476-9_43
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-83478-3
Online ISBN: 978-3-642-83476-9
eBook Packages: Springer Book Archive