Abstract
In this work we propose an approach to estimate perplexity values for complex language models such as a language model based on phrase classes. The perplexity values obtained by using this method are compared to other typically employed approaches and to the perplexity obtained without any simplification. Experiments over two different corpora were carried out and it can be concluded that the proposed approach provides a good estimation of the perplexity while reduces the computational cost.
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
Justo, R., Torres, M.I.: Phrase classes in two-level language models for ASR. Pattern Analysis and Applications Journal (in press) (2008)
Yamamoto, H., Isogai, S., Sagisaka, Y.: Multi-class composite n-gram language model. Speech Communication 41(2-3), 369–379 (2003)
Zitouni, I.: A hierarchical language model based on variable-length class sequences: the mcni approach. IEEE Trans. on Speech and Audio Proc. 10(3), 193–198 (2002)
García, P., Vidal, E.: Inference of k-testable languages in the strict sense and application to syntactic pattern recognition. IEEE Trans. Pattern Anal. Mach. Intell. 12(9), 920–925 (1990)
Torres, I., Varona, A.: k-tss language models in speech recognition systems. Computer Speech and Language 15(2), 127–149 (2001)
Benedí, J., Lleida, E., Varona, A., Castro, M., Galiano, I., Justo, R., López, I., Miguel, A.: Design and acquisition of a telephone spontaneous speech dialogue corpus in Spanish: DIHANA. In: Proc. of LREC 2006, Genoa, Italy (May 2006)
Och, F.J.: An efficient method for determining bilingual word classes. In: Proceedings of the ninth conference on European chapter of the ACL, Bergen, Norway, pp. 71–76 (1999)
Justo, R., Torres, M.I.: Two approaches to class-based language models for asr. In: IEEE Workshop on MLSP, Thessaloniki, Greece, August 27-29 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Justo, R., Torres, M.I. (2009). An Approach to Estimate Perplexity Values for Language Models Based on Phrase Classes. In: Araujo, H., Mendonça, A.M., Pinho, A.J., Torres, M.I. (eds) Pattern Recognition and Image Analysis. IbPRIA 2009. Lecture Notes in Computer Science, vol 5524. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02172-5_53
Download citation
DOI: https://doi.org/10.1007/978-3-642-02172-5_53
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02171-8
Online ISBN: 978-3-642-02172-5
eBook Packages: Computer ScienceComputer Science (R0)