Abstract
We present two approaches to cluster dialogue-based information obtained by the speech understanding module and the dialogue manager of a spoken dialogue system. The purpose is to estimate a language model related to each cluster, and use them to dynamically modify the model of the speech recognizer at each dialogue turn. In the first approach we build the cluster tree using local decisions based on a Maximum Normalized Mutual Information criterion. In the second one we take global decisions, based on the optimization of the global perplexity of the combination of the cluster-related LMs. Our experiments show a relative reduction of the word error rate of 15.17%, which helps to improve the performance of the understanding and the dialogue manager modules.
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
Bahl, R.L., Brown, P.F., de Souza, P.V., Mercer, R.L.: Maximum Mutual Information Estimation of Hidden Markov Model Parameters for Speech Recognition. In: Proc. ICASSP, pp. 49–52 (1986)
Bellegarda, J.R., Butzberger, J.W., Chow, Y.L., Coccaro, N.B., Naik, D.: A Novel Word Clustering Algorithm Based on Latent Semantic Analysis. In: Proc. ICASSP, vol. I, pp. 172–175 (1996)
Bellegarda, J.R.: Statistical language model adaptation: review and perspectives. Speech Comm. 42, 93–108 (2004)
Fernández, F., Ferreiros, J., Sama, V., Montero, J.M., San-Segundo, R., Macías-Guarasa, J.: Speech Interface for Controlling a Hi-Fi Audio System Based on a Bayesian Belief Networks Approach for Dialog Modeling. In: Proc. INTERSPEECH, pp. 3421–3424 (2005)
GuoDong, Z., KimTeng, L.: Interpolation of n-gram and mutual-information based trigger pair language models for Mandarin speech recognition. Comp. Speech & Lang. 13, 125–141 (1999)
Kneser, R., Steinbiss, V.: On the dynamic adaptation of stochastic language models. In: Proc. ICASSP, vol. II, pp. 586–589 (1993)
Lucas-Cuesta, J.M., Fernández, F., Ferreiros, J.: Using Dialogue-Based Dynamic Language Models for Improving Speech Recognition. In: INTERSPEECH, pp. 2471–2474 (2009)
Lucas-Cuesta, J.M., Fernández, F., López, V., Ferreiros, J., San-Segundo, R.: Clustering of syntactic and discursive information for the dynamic adaptation of Language Models. In: SEPLN, vol. 45, pp. 175–182 (2010)
Solsona, R.A., Fosler-Lussier, E., Kuo, H.K.J., Potamianos, A., Zitouni, I.: Adaptive Language Models for Spoken Dialogue Systems. In: Proc. ICASSP, vol. I, pp. 37–40 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lucas-Cuesta, J.M., Fernández-Martínez, F., Moreno, T., Ferreiros, J. (2012). Mutual Information and Perplexity Based Clustering of Dialogue Information for Dynamic Adaptation of Language Models. In: Torre Toledano, D., et al. Advances in Speech and Language Technologies for Iberian Languages. Communications in Computer and Information Science, vol 328. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35292-8_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-35292-8_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35291-1
Online ISBN: 978-3-642-35292-8
eBook Packages: Computer ScienceComputer Science (R0)