Abstract
The usage of multiple Hidden Markov Models (HMMs) to construct a Czech speech segment database (SSD) and a speech synthesis based on this inventory are presented in this paper. HMMs are used to model triphones. Binary decision trees are applied to automatically cluster the states of triphone HMMs. The clustered states are then employed to automatically segment the speech corpus and to create a SSD. The SSD constructed in this way is assumed to enable more precise context modeling than was previously possible. Several speech techniques are discussed to construct a concatenation-based synthesizer. Special attention is paid to an MFCC-based pitch-synchronous residually excited approach.
This work was supported by the project No. VS97159 of the Ministry of Education of Czech Republic
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
Donovan R.E., Eide M.: The IBM Trainable Speech Synthesis System. Proceedings of ICSLP’98, Sydney (1998).
Huang X., Acero A., Adcock J., Hon H-W., Goldsmith J., Liu J., and Plumpe M.: Whistler: A Trainable Text-to-Speech System; Proceedings of ICSLP’96, Philadelphia, (1996) 2387–2390.
Davis S., Mermelstein P.: Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences. IEEE Trans. ASSP, ASSP-28 (1980) 357–366.
Tychtl Z., Psutka J.: Speech Production Based on the Mel-Frequency Cepstral Co-efficients. Proceedings of Eurospeech’99 (1999).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Matoušek, J., Psutka, J., Tychtl, Z. (1999). Statistical Approach to the Automatic Synthesis of Czech Speech. In: Matousek, V., Mautner, P., Ocelíková, J., Sojka, P. (eds) Text, Speech and Dialogue. TSD 1999. Lecture Notes in Computer Science(), vol 1692. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48239-3_72
Download citation
DOI: https://doi.org/10.1007/3-540-48239-3_72
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66494-9
Online ISBN: 978-3-540-48239-0
eBook Packages: Springer Book Archive