For accurate speech recognition, a well-defined language model is necessary. When a large amount of learning texts (corpus) is available, a statistical language model such as bi-gram or tri-gram generated from a corpus is quite powerful. For example, most of current dictation systems employ bi-gram or tri-gram language models. However, if the size of the corpus is not sufficiently large, reliability of statistical information calculated from the corpus decreases and then so does the effectiveness of the generated statistical language model (sparseness problem). Furthermore, preparing a sufficient amount of texts for spoken language is generally very expensive. Therefore, a finite state automaton (FSA) language model is generally used for small- or middle-size (around 1000 words) vocabulary speech recognition. However, defining a FSA model by hand requires much human effort. In some systems, a FSA model is automatically generated by converting from regular-grammar type grammar rules (e.g., see Hparse [1]), but it is still a very time- and effort-consuming task to prepare a grammar with sufficient coverage and consistency.
In this chapter, we propose a new method to construct a FSA language model, by using a FSA DP (dynamic programming) matching method. We also report some experimental results; the method was applied to a travel conversation corpus (with about a thousand sentences) to generate a FSA model, and then, speech recognition experiments using the language model were conducted. The result shows that the recognition correct rate is high enough for closed data, but is not so satisfactory for open data. To cope with this problem, we also propose an additional mechanism that decides whether a recognized result can be accepted or should be rejected by evaluating a distance of the result from the learning corpus. After the mechanism is applied, the recognition correct rate for accepted results is considerably improved.
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
S. Young et al.: The HTK Book (for Ver. 3.0), 1999 (http://htk.eng.cam.ac.uk/)
K. J. Lang, B. A. Pearlmutter, and R. Price: Results of the Abbadingo one DFA learning competition and a new evidence driven state merging algorithm, Proceedings of International Colloquium Grammatical Inference, pp. 1–12, 1998
S. M. Lucas and T. J. Reynolds: Learning deterministic finite automata with a smart state labeling evolutionary algorithm, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, No. 7, July 2006
C. Kermorvant, C. de la Hinguera, and P. Dupont: Learning typed automata from automatically labeled data, Journal Électronique d’Intelligence Artificielle, Vol. 6, No. 45, 2004
J. Hu, W. Turin, and M. K. Brown: Language modeling with stochastic automata, Proceedings of International Conference on Spoken Language Processing (ICSLP)-1996, 1996
G. Riccardi, R. Pieraccini, and E. Boccieri: Stochastic automata for language modeling, Computer Speech and Language, Vol. 10, No. 4, pp. 265–293, 1996
A. V. Aho, J. D. Ullman, and J. E. Hopcroft: Data Structures and Algorithms, Addison-Wesley, 1983
T. Kawahara, A. Lee, K. Takeda, K. Itou, and K. Shikano: Recent progress of open-source lvcsr engine julius and japanese model repository—Software of continuous speech recognition consortium, Proceedings of International Conference on Spoken Language Processing (ICSLP)-2004, 2004 (http://julius.sourceforge.jp/en/julius.html)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
Morimoto, T., Takahashi, Sy. (2008). Automatic Construction of FSA Language Model for Speech Recognition by FSA DP-Matching. In: Castillo, O., Xu, L., Ao, SI. (eds) Trends in Intelligent Systems and Computer Engineering. Lecture Notes in Electrical Engineering, vol 6. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-74935-8_36
Download citation
DOI: https://doi.org/10.1007/978-0-387-74935-8_36
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-74934-1
Online ISBN: 978-0-387-74935-8
eBook Packages: EngineeringEngineering (R0)