In this paper we present an innovative approach to speech understanding which is based on a fine-grained knowledge representation automatically compiled from a semantic network and on iterative optimization. Besides allowing an efficient exploitation of parallelism, any-time capability is provided since after each iteration step a (sub-)optimal solution is always available. We apply this approach to a real-world task, which is a dialog system able to answer queries about the German train timetable. In order to speed up the search for the best interpretation of an utterance we make use of statistical methods, e.g. neural networks, n-grams, and classification trees, which are trained on application relevant utterances collected over the public telephone network. At the moment the real-time factor for interpreting the initial user's utterance is 0.7.
Cite as: Fischer, J., Haas, J., Nöth, E., Niemann, H., Deinzer, F. (1998) Empowering knowledge based speech understanding through statistics. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0369, doi: 10.21437/ICSLP.1998-482
@inproceedings{fischer98b_icslp,
author={Julia Fischer and Juergen Haas and Elmar Nöth and Heinrich Niemann and Frank Deinzer},
title={{Empowering knowledge based speech understanding through statistics}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0369},
doi={10.21437/ICSLP.1998-482}
}