Abstract
In this paper we describe the work done to build a new voice based on diphone concatenation in the Spanish spoken in Mexico. This voice is compatible with the Text to Speech Synthesis System Festival. In the development of each module of the system the own features of Spanish were taken into account. In this work we hope to enhance the naturalness of the synthesized voice by including a prosodic model. The prosodic factors taken into consideration by the model are: phrasing, accentuation, duration and F0 contour. Duration and F0 prediction models were trained from natural speech corpora. We found the best prediction models by testing several machine learning methods and two different corpora. The paper describes the building, and training process as well as the results and their respective interpretation.
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
Dutoit, T.: An Introduction to Text-to-Speech Synthesis. Kluwer Academic Publishers, Dordrecht (1997) (Text, Speech and Language Technology, 3)
The Centre for Speech Technology Research (CSTR): The University of Edimburgh. Internet Page, http://www.cstr.ed.ac.uk/projects/festival/
Meza, H.: Modelos Estadísticos de Duraciones de los Fonemas en el Español Mexicano. Master Thesis, Universidad de las Américas - Puebla, Dept. of Computer Systems Engineering (1999)
Black, A., Taylor, P., Macon, M.: Speech Synthesis in Festival A practical course on making computers talk Edition 2.0, for Festival Version 1.4.1 (2000)
Black, A., Lenzo, K.: Building Synthetic Voices for FestVox 2.0 Edition (2003)
Barbosa, A.: Desarrollo de una nueva voz en Español de México para el Sistema de Texto a Voz Festival, Master Thesis, Universidad de las Américas - Puebla, Dept. of Computer Systems Engineering (1997)
Black, A., Taylor, P., Macon, M.: The Festival Speech Synthesis System: System documentation. Technical Report HCRC/TR-83, Human Communciation Research Centre, University of Edinburgh, Scotland, UK (1997)
Jun, S.-A.: Prosodic Phrasing and Attachment Preferences. Journal of Psycholinguistic Research 32(2), 219–249 (2003)
Schötz, S.: Prosody in Relation to Paralinguistic Phonetics - Earlier and Recent Definitions, Distinctions and Discussions. Term paper for course in Prosody, Lund University, Dept. of Linguistics and Phonetics (2003)
Pineda, L., Villaseñor, L., Cuetara, J., Castellanos, H., Lopez, I.: A New Phonetic and Speech Corpus for Mexican Spanish. In: Lemaître, C., Reyes, C.A., González, J.A. (eds.) IBERAMIA 2004. LNCS (LNAI), vol. 3315, pp. 974–983. Springer, Heidelberg (2004) ISSN: 0302-9743, ISBN 3-540-23806-9
The University of Waikato: Hamilton, New Zealand Web Page, http://www.cs.waikato.ac.nz/ml/1999-2004
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Espinosa, H.P., García, C.A.R. (2005). Building and Training of a New Mexican Spanish Voice for Festival. In: Gelbukh, A., de Albornoz, Á., Terashima-Marín, H. (eds) MICAI 2005: Advances in Artificial Intelligence. MICAI 2005. Lecture Notes in Computer Science(), vol 3789. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11579427_89
Download citation
DOI: https://doi.org/10.1007/11579427_89
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29896-0
Online ISBN: 978-3-540-31653-4
eBook Packages: Computer ScienceComputer Science (R0)