Abstract
Information about the dialogue-state can be integrated into language models to improve performance of the speech recogniser in a dialogue system. A dialogue state is defined in this paper as the question, the user is replying to. One of the main problems in dialogue-state dependent language modelling is the limitation of training data. In order to obtain robust models, we use the method of rational interpolation to smooth between a dialogue-state dependent and a general language model. In contrast to linear interpolation methods, rational interpolation weights the different predictors according to their reliability. Semantic-pragmatic knowledge is used to enlarge the training data of the language models. Both methods reduce perplexity and word error rate significantly.
This is a preview of subscription content, log in via an institution to check access.
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
W. Eckert and F. Gallwitz and H. Niemann: Combining Stochastic and Linguistic Language Models for Recognition of Spontaneous Speech. Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Atlanta, USA (1996) 423–426.
F. Gallwitz and M. Aretoulaki and M. Boros and J. Haas and S. Harbeck and R. Huber and H. Niemann and E. Nöth: The Erlangen Spoken Dialogue System EVAR: A State-of-the-Art Information Retrieval System. Proceedings of 1998 International Symposium on Spoken Dialogue, Sydney, Australia (1998) 19–26.
G. Riccardi and A. L. Gorin: Stochastic Language Adaptation Over Time and State in a Natural Spoken Dialog System. IEEE Trans. on Speech and Audio Proc., Vol. 8, No. 1, January 2000 3–10.
E.G. Schukat-Talamazzini and F. Gallwitz and S. Harbeck and V. Warnke: Rational Interpolation of Maximum Likelihood Predictors in Stochastic Language Modeling. Proc. European Conf. on Speech Communication and Technology, Rhodes, Greece, (1997) 2731–2734.
F. Wessel and A. Baader: Robust Dialogue-State Dependent Language Modeling Using Leaving-One-Out. Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Phoenix, USA (1999) 741–744.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Stemmer, G., Nöth, E., Niemann, H. (2000). The Utility of Semantic-Pragmatic Information and Dialogue-State for Speech Recognition in Spoken Dialogue Systems. In: Sojka, P., Kopeček, I., Pala, K. (eds) Text, Speech and Dialogue. TSD 2000. Lecture Notes in Computer Science(), vol 1902. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45323-7_74
Download citation
DOI: https://doi.org/10.1007/3-540-45323-7_74
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41042-3
Online ISBN: 978-3-540-45323-9
eBook Packages: Springer Book Archive