Abstract
In this paper, the influence of intonation to recognize dialogue acts from speech is assessed. Assessment is based on an empirical approach: manually tagged data from a spoken-dialogue and video corpus are used in a CART-style machine learning algorithm to produce a predictive model. Our approach involves two general stages: the tagging task, and the development of machine learning experiments. In the first stage, human annotators produce dialogue act taggings using a formal methodology, obtaining a highly enough tagging agreement, measured with Kappa statistics. In the second stage, tagging data are used to generate decision trees. Preliminary results show that intonation information is useful to recognize sentence mood, and sentence mood and utterance duration data contribute to recognize dialogue act. Precision, recall and Kappa values of the predictive model are promising. Our model can contribute to improve automatic speech recognition or dialogue management systems.
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
Allen, J.F., Core, M.: Draft of DAMSL: Dialog Act Markup in Several Layers. Technical report, The Multiparty Discourse Group. University of Rochester, Rochester, USA (October 1997)
Pineda, L., Castellanos, H., Coria, S., Estrada, V., López, F., López, I., Meza, I., Moreno, I., Pérez, P., Rodríguez, C.: Balancing Transactions in Practical Dialogues. In: CIC-LING 2006, Centro de Investigacion en Computacion, Instituto Politecnico Nacional, Mexico City (February 2006)
Pineda, L., Massé, A., Meza, I., Salas, M., Schwarz, E., Uraga, E., Villaseñor, L.: The DIME Project. In: Coello Coello, C.A., de Albornoz, Á., Sucar, L.E., Battistutti, O.C. (eds.) MICAI 2002. LNCS (LNAI), vol. 2313, pp. 166–175. Springer, Heidelberg (2002)
Jekat, S., Klein, A., Maier, E., Maleck, I., Mast, M., Quantz, J.J.: Dialogue Acts in VERBMOBIL., VM-Report 65, Universitat Hamburg, DFKI Saarbrucken, Universitat Erlangen, TU Berlin (April 1995)
Cuetara-Priede, J., Villaseñor-Pineda, L., Pineda-Cortes, L.: A New Phonetic and Speech Corpus for Mexican Spanish. In: Iberamia 2004, INAOE, Tonantzintla, Pue., Mexico (2004)
Villaseñor, L., Massé, A., Pineda, L.: The DIME Corpus. In: ENC 2001, 3er Encuentro Internacional de Ciencias de la Computación, SMCC-INEGI, Aguascalientes, Mexico (2001)
Shriberg, E., Bates, R., Stolcke, A., Taylor, P., Jurafsky, D., Ries, K., Coccaro, N., Martin, R., Meteer, M., Van EssDykema, C.: Can Prosody Aid the Automatic Classification of Dialog Acts in Conversational Speech? In: Language and Speech 41(3-4), pp. 439–487 (1998) Special Issue on Prosody and Conversation, USA
Hirst, D., Di Cristo, A., Espesser, R.: Levels of representation and levels of analysis for the description of intonation systems. In: Horne, M. (ed.) Prosody: Theory and Experiment. Kluwer, Dordrecht (2000)
Hirst, D., Espesser, R.: Automatic modeling of fundamental frequency using a quadratic spline function. Technical report, CNRS (URA 261), Institut de Phonétique d’Aix, Université de Provence, France (1993)
Espesser, R.: MES: Motif Environment for Speech software (1999), http://www.lpl.univ-aix.fr/ext/projects/mes_signaix.htm
Carletta, J.: Assessing agreement on classification tasks: the kappa statistic. Computational Linguistics, Association for Computational Linguistics, USA 22(2), 249–254 (1996)
Craggs, R., McGee Wood, M.: Evaluating Discourse and Dialogue Coding Schemes. Computational Linguistics, Association for Computational Linguistics, USA 31(3), 289–295 (2005)
Coria, S., Pineda, L.: Predicting obligation dialogue acts from prosodic and speaker infomation. In: Research on Computing Science, Centro de Investigacion en Computacion, Instituto Politecnico Nacional, Mexico City (September 2005) (ISSN 1665-9899)
Witten, I., Frank, E.: Data Mining. In: Practical Machine Learning Tools and Techniques with Java implementations. Morgan-Kauffman Publishers, San Francisco (2000)
Frank, E., Hall, M., Trigg, L.: WEKA: Waikato Environment for Knowledge Analysis software (2004), http://www.cs.waikato.ac.nz/~ml/weka
Coria, S., Pineda, L.: Predicting obligation dialogue act types from prosodic information. In: 2nd Midwest Computational Linguistics Colloquium, Ohio State University, USA (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Olguin, S.R.C., Cortés, L.A.P. (2006). Predicting Dialogue Acts from Prosodic Information. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2006. Lecture Notes in Computer Science, vol 3878. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11671299_37
Download citation
DOI: https://doi.org/10.1007/11671299_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-32205-4
Online ISBN: 978-3-540-32206-1
eBook Packages: Computer ScienceComputer Science (R0)