Abstract
In this paper we apply a Naïve Bayes classifier (NB), a Bayesian Network (BAN) and a decision tree inducer (CART) on predicting Pitch Accent tones in Greek text, extracting knowledge from text and linguistic information. It is well established that regarding the performance of machine learning techniques, scale and quality of the corpus are very important. For our purpose we used a database consisted of 5.500 words, distributed in 500 paragraphs. In the present study, pitch accent placement was treated as a binary classification task. Hence, given a word form in its sentential context, it was decide whether it should be unaccented or bear a pitch accent tone.
This work was supported by the “Infotainment management with Speech Interaction via Remote microphones and telephone interfaces” – INSPIRE project (IST-2001-32746).
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
Arvaniti, A., Baltazani, M.: GREEK ToBI: A System for the Annotation of Greek Speech Corpora. In: LREC, vol. II, p. 555562 (2000)
Conkie, A., Riccardi, G., Rose, R.C.: Prosody recognition from speech utterances using acoustic and linguistic based models of prosodic event. In: Proc. Of Eurospeech, Budapest, Hungary, pp. 523–526 (1999)
Heckerman, D., Geiger, D., Chickering, D.M.: Learning Bayesian networks: the combination of knowledge and statistical data. Machine Learning 20, 197–243 (1995)
Hirschberg, J.: Pitch accent in context: predicting intonational prominence from text. Artificial Intelligence 63, 305–340 (1993)
Mitchell, T.: Machine Learning. McGraw-Hill, New York (1997)
Muller, A.F., Hoffmann, R.: A neural network model and a hybrid approach for accent label prediction. In: Proc. Of the 4th ISCA Tutorial and Research Workshop on Speech Synthesis, Perthshire, Scotland (2001)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Mateo (1988)
Pierrehumbert, J.: Synthesizing intonation. Journal of the Acoustical Society of America 70(4), 985–995 (1981)
Pierrehumbert, J.: The Phonology and Phonetics of English Intonation, Ph.D. dissertation, MIT, Indiana University Linguistics Club (1980)
Ross, K., Ostendorf, M.: A dynamical system model for recognizing intonation patterns. In: Proc. of Eurospeech, Madrid, pp. 993–996 (1995)
Taylor, P., Black, A.: Assigning Phrase Breaks from partofspeech Sequences. Computer Speech and Language 12, 99–117 (1998)
Silverman, K., Beckman, M.E., Pitrelli, J., Ostendorf, M., Wightman, C., Price, P., Pierrehumbert, J., Hirschberg, J.: ToBI: a standard for labelling English prosody. In: ICSLP 1992, vol. 2, pp. 867–870 (1992)
Stamatatos, E., Fakotakis, N., Kokkinakis, G.: A Practical Chunker for Unrestricted Text. In: Proceedings of the 2nd International Conference of Natural Language Processing, pp. 139–150 (2000)
Sun, X.: Pitch accent prediction using ensemble machine learning. In: Proc of ICSLP 2002, Denver, Colorado, September 16-20 (2002)
Taylor, P., Caley, R., Black, W.A., King, S.: Edinburgh Speech Tools Library, System Documentation Edition 1.2 CSTR, University of Edinburgh (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zervas, P., Fakotakis, N., Kokkinakis, G. (2004). Pitch Accent Prediction from ToBI Annotated Corpora Based on Bayesian Learning. In: Sojka, P., Kopeček, I., Pala, K. (eds) Text, Speech and Dialogue. TSD 2004. Lecture Notes in Computer Science(), vol 3206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30120-2_69
Download citation
DOI: https://doi.org/10.1007/978-3-540-30120-2_69
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23049-6
Online ISBN: 978-3-540-30120-2
eBook Packages: Springer Book Archive