Abstract
The main drawback of older methods of prosody modelling is the monotony of the output, which is perceived as uncomfortable by the users, especially when listening to longer passages. The present paper proposes a prosodic generator designed to increase the variability of synthesized speech in reading devices for the blind. The method used is based on text segmentation into several prosodic patterns by means of vector quantisation and the subsequent training of corresponding HMMs (Hidden Markov Models) on F0 parameters. The path through the model’s states is then used to generate sentence prosody. We also tried to utilize morphological information in order to increase prosody naturalness. The evaluation of the quality of the proposed prosodic generators was carried out by means of listening tests.
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
Rajeswari, K.C., Uma, M.P.: Prosody Modeling Techniques for Text-to-Speech Synthesis Systems – A Survey. International Journal of Computer Applications 39(16), 8–11 (2012)
Malfrère, F., Dutoit, T., Mertens, P.: Automatic Prosody Generation Using Suprasegmental Unit Selection. In: Proc. ESCA Workshop on Speech Synthesis, pp. 323–328 (1998)
Bellur, A., Narayan, K.B., Raghava, K.K., Murthy, H.A.: Prosody modeling for syllable based concatenative speech synthesis of Hindi and Tamil. In: National Conference on Communications, pp. 28–30 (2011)
Chaloupka, Z., Uhlíř, J.: Speech Defect Analysis Using Hidden Markov Models. Radioengineering (2007)
Hardcastle, W.J., Laver, J., Gibbon, F.E.: The Handbook of Phonetic Sciences (2009) ISBN 978-1-4051-4590-9
Deza, M.M., Deza, E.: Dictionary of distances. Elsevier (2006) ISBN-13: 978-0-444-52087-6
Bořil, H.: Robust speech recognition: Analysis and equalization of Lombard effect in Czech corpora, Ph.D. dissertation, Czech Technical University in Prague, Czech Republic (2008)
Hajič, J.: Complex Corpus Annotation: The Prague Dependency Treebank. Jazykovedný ústav Ľ. Štúra, SAV, Bratislava, Slovakia (2004)
Žabokrtský, Z., Ptáček, J., Pajas, P.: TectoMT: Highly Modular MT System with Tectogrammatics Used as Transfer Layer. In: Proceedings of WMT (2008)
Sokal, R.R., Rohlf, F.J.: Biometry: The principles and practice of statistics in biological research, 3rd edn. W.H. Freeman, New York (1995)
D’Agostino, R.B.: Tests for the Normal Distribution. In: D’Agostino, R.B., Stephens, M.A. (eds.) Goodness-of-Fit Techniques. Marcel Dekker, New York (1986) ISBN 0-8247-7487-6
Epos system, http://epos.ufe.cz
Žabokrtský, Z., Bojar, O.: TectomMT - Developer’s Guide, http://ufal.mff.cuni.cz/tectomt/guide/guidelines.html
HTK software, Ver. 3.2.1., http://htk.eng.cam.ac.uk
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
Chaloupka, Z., Horák, P. (2012). Prosody Modelling for TTS Systems Using Statistical Methods. In: Esposito, A., Esposito, A.M., Vinciarelli, A., Hoffmann, R., Müller, V.C. (eds) Cognitive Behavioural Systems. Lecture Notes in Computer Science, vol 7403. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34584-5_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-34584-5_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34583-8
Online ISBN: 978-3-642-34584-5
eBook Packages: Computer ScienceComputer Science (R0)