Abstract
In this paper, we propose a simple and effective method for speech understanding. The method incorporates some speech recognizers. We use two types of recognizers; a large vocabulary continuous speech recognizer and a domain-specific speech recognizer. The multiple recognizer is a robust and flexible method for speech understanding. Words in different utterances often contain relations. For example, users frequently input the parameter value after speaking command names to a system. We handle the relation by a hierarchical multiple recognizer. We compared the proposed method with a non-hierarchical method. Our method outperformed the non-hierarchical method.
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.
Similar content being viewed by others
References
Bouwman, C., Sturm, J., Boves, L.: Incorporating confidence measures in the dutch train timetable information system developed in the arice project. In: Proceedings of ICASSP (1999)
Komatani, K., Kawahara, T.: Flexible mixed-initiative dialogue management using concept-level confidence measures of speech recognizer output. In: Proceedings of COLING 2000, vol. 1, pp. 467–473 (2000)
Komatani, K., Fukubayashi, Y., Ogata, T., Okuno, H.G.: Introducing utterance verification in spoken dialogue system to improve dynamic help generation for novice users. In: Proceedings of the 8th SIGdial Workshop on Discourse and Dialogue, pp. 202–205 (2007)
Sako, A., Takiguchi, T., Ariki, Y.: System request discrimination based on adaboost. In: IPSJ Technical Report. SIG-SLP64, pp. 19–24 (2006)
Shimada, K., Horiguchi, S., Endo, T.: An effective speech understanding method with a multiple speech recognizer based on output selection using edit distance. In: Proceedings of the 22nd Pacific Asia Conference on Language, Information and Computation (PACLIC22), pp. 350–357 (2008)
Lane, I.R., Kawahara, T., Matsui, T., Nakamura, S.: Dialogue speech recognition by combining hierarchical topic classification and language model switching. IEICE Transaction on Information and Systems, ED 88(3), 446–454 (2005)
Lee, A., Kawahara, T., Shikano, K.: Julius - an open source real-time large vocabulary recognition engine. In: Proceedings of Eurospeech, pp. 1691–1694 (2001)
Isobe, T., Itou, K., Takeda, K.: A likelihood normalization method for the domain selection in the multi-decoder speech recognition system. IEICE Transaction on Information and Systems (Japanese Edition) 90(7), 1773–1780 (2007)
Shimada, K., Uzumaki, A., Kitajima, M., Endo, T.: Speech understanding in a multiple recognizer with an anaphora resolution process. In: Proceedings of the 11th Conference of the Pacific Association for Computational Linguistics (PACLING 2009), pp. 262–267 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yokoyama, T., Shimada, K., Endo, T. (2010). A Hierarchical Multiple Recognizer for Robust Speech Understanding. In: Zhang, BT., Orgun, M.A. (eds) PRICAI 2010: Trends in Artificial Intelligence. PRICAI 2010. Lecture Notes in Computer Science(), vol 6230. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15246-7_73
Download citation
DOI: https://doi.org/10.1007/978-3-642-15246-7_73
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15245-0
Online ISBN: 978-3-642-15246-7
eBook Packages: Computer ScienceComputer Science (R0)