Abstract
In this paper a technique for detection and rejection of incorrectly recognized words is described. The speech recognition system we used is based on a speaker-independent continuous density Hidden Markov Model recognizer and socalled mumble model, which structure and function is also depicted. An improved rejection technique is presented in comparison with the heuristic rejection method that we previously used. The new method is fully statistically based. Therefore selection of features for training and classification, procedures for statistical models parameters estimation, and experimental results are reported. The improved rejection technique achieves approximately 12% error rate in detection of incorrectly recognized words.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Kittler, J., Young, P. C.: A New Approach to Feature Selection Based on the Karhunen Loeve Expansion. Pattern Recognition, 1973, n. 4, pp. 335–352.
Fukunaga, K., Koontz, W. L. G.: Application of the Karhunen Loeve Expansion to Feature Selection and Ordering. IEEE Trans. on Computers, C-19 (1970), n. 4, pp. 311–318.
Müller, L., Jurčíček F., Šmídl, L.: Rejection and Key-Phrase Spotting Techniques Using a Mumble Model in a Czech Telephone Dialogue System, Proceedings of the 6th International Conference on Spoken Language Processing ICSLP 2000, Beijing, China, 2000, pp. 134–137.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bartoš, T., Müller, L. (2002). Rejection Technique Based on the Mumble Model. In: Sojka, P., Kopeček, I., Pala, K. (eds) Text, Speech and Dialogue. TSD 2002. Lecture Notes in Computer Science(), vol 2448. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46154-X_30
Download citation
DOI: https://doi.org/10.1007/3-540-46154-X_30
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44129-8
Online ISBN: 978-3-540-46154-8
eBook Packages: Springer Book Archive