Abstract
The article deals with the problem of continuous speech recognition of Czech language. The main goal of this study is to compare various kinds of bigram language models with respect to the accuracy and speed of speech recognition. The main types of bigram language models are described here as well as multiple parameters that affect the performance of a speech recognition system. A comparison with a zerogram model is also made. Different models and various parameter settings are compared by means of the accuracy rate in extensive experiments done with a large test database of 1,600 Czech sentences recorded by 40 speakers.
This work has been supported by the Grant Agency of the Czech Republic (grant no. 102/02/0124) and through research goal project MSM 242200001.
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
Nouza, J.: A Czech Large Vocabulary Recognition System for Real-Time Applications. In: P. Sojka et al. (Eds.): Proc. of 3rd International Workshop on Text, Speech, Dialogue, Springer-Verlag, Heidelberg, Germany (2000) 217–222.
Nouza, J.: Strategies for Developing a Real-Time Continuous Speech Recognition System for Czech Language. In: Sojka P. et al. (Eds.): Text, Speech and Dialogue, Proceedings of the Fifth International Conference, Brno, Czech Republic, September 9–12, 2002, pp. 189–196.
Witten, I. H. and Bell, T.C.: The Zero-Frequency Problem: Estimating the Probabilities of Novel Events in Adaptive Text Compression. IEEE Transactions on Information Theory, 37(4), (1991) 1085–1094.
Jelinek, F. and Mercer, R. L.: Interpolated Estimation on Markov Source Parameters from Sparse Data. In Gelsema, E. S. and Kanal, L.N. (Eds.), Proceedings, Workshop on Pattern Recognition in Practice. North Holland, Amsterdam (1980) 381–397.
Katz, S. M.: Estimation of Probabilities from Sparse Data for the Language Model Component of a Speech Recognizer. IEEE Transactions on Acoustics, Speech, and Signal Processing, 35(3), (1987) 400–401.
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
Nejedlová, D. (2002). Comparative Study on Bigram Language Models for Spoken Czech Recognition. 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_27
Download citation
DOI: https://doi.org/10.1007/3-540-46154-X_27
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