Abstract
The paper deals with the problem of choosing and optimizing the inventories of speechse gments (especially with respect to the concatenative speech synthesis). We offer taxonomy of the segment databases based on elementary properties of the segments in relation to a basic speech corpus. Next, we deal with a general abstract formulation of the problem and briefly discuss its algorithmic solution and applications.
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
E.C. Albano, P.A. Aquino: Linguistic Criteria for Building and Recording Units for Concatenative Speech Synthesis in Brazilian Portuguese, in Proceedings of Eurospeech, Rhodes, Greece, pp. 725–728, 1997.
J. Černocky, I. Kopeček, G. Baudoin, G. Chollet: Very Low Bit Rate Speech Coding: Comparison of Data-Driven Units with Syllable Segments; in Proceedings of the Workshop on Text, Speech and Dialogue-TSD’99, Lectures Notes in Artificial Intelligence 1692, Springer-Verlag, 1999, pp. 262–267.
S. Deligne, F. Bimbot: Inference of Variable-Length Linguistic and Acoustic Units by Multigrams, Speech Communication 23 (1997), 223–241.
G. Doddington: Syllable Based Speech Processing; WS97 Project Report, Research Notes No. 30, J. Hopkins University, 1997.
S. Greenberg: Speaking in Shorthand — A Syllable-Centric Perspective for Understanding Pronunciation Variation; Proceedings of the workshop Modeling Pronunciation Variation for Automatic Speech Recognition, 1998, pp.47–56.
T. Dutoit: An Introduction to Text-to-Speech Synthesis, Kluwer Academic Publishers, 1997.
A.J. Hunt, A.W. Black: Unit Selection in A Concatenative Speech Synthesis System Using a Large Database, in Proceedings of ICSLP, Philadelphia, pp. 373–376, 1996.
L. Josifovski, D. Mihajlov, D. Gorgevik: Speech Synthesizer Based on Time Domain Syllable Concatenation; Proceedings SPECOM’97, Cluj-Napoca, 1997, pp. 165–170.
I. Kopeček: Syllable Based Approach to Automatic Prosody Detection; Applications for Dialogue Systems; in Proceedings of the Workshop on Dialogue and Prosody, Veldhoven, 1999, pp. 89–92.
I. Kopeček: Speech Synthesis Based on the Composed Syllable Segments; Proceedings of the First Workshop on Text, Speech and Dialogue-TSD’98, 1998, pp. 259–262.
I. Kopeček: Automatic Segmentation into Syllable Segments; Proceedings of First Int. Conference on Language Resources and Evaluation, 1998, pp. 1275–1279.
I. Kopeček: Syllable Based Speech Synthesis; Proceedings of the 2nd International Workshop SPECOM’97, Cluj-Napoca, 1997, pp. 161–165.
I. Kopeček: Databases of Speech Segments; FI MU Technical Reports, to appear.
I. Kopeček, K. Pala: Prosody Modelling for Syllable-Based Speech Synthesis; Proceedings of the IASTED Conference on AI and Soft Computing, 1998, pp 134–137.
K. Osolsobe, K. Pala, Stem Dictionary for IBM PC, Proceedings of the Conference on the Computer Lexicography, Balatonfured, 1990.
R. Sedláček, A Morphological Analyzer for Czech (in Czech), Diploma Thesis, Brno, Masaryk University, 1999.
J.R.W. Yi, J.R. Glass: Natural-Sounding Speech Synthesis Using Variable-Lengths Units.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kopeček, I. (2001). Algebraic Models of Speech Segment Databases. In: Matoušek, V., Mautner, P., Mouček, R., Taušer, K. (eds) Text, Speech and Dialogue. TSD 2001. Lecture Notes in Computer Science(), vol 2166. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44805-5_27
Download citation
DOI: https://doi.org/10.1007/3-540-44805-5_27
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42557-1
Online ISBN: 978-3-540-44805-1
eBook Packages: Springer Book Archive