Design and Implementation of a Text-to-Speech System using the Prosody and Duration Information


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 3, No. 5, pp. 1121-1129, Sep. 1996
10.3745/KIPSTE.1996.3.5.1121,   PDF Download:

Abstract

To produce more natural speech in a Text-to-speech system, the processing of the prosody and duration must be preceded. For this, we applied a sequence of intonation rules to the sentences analyzed by natural language processing in advance, and then extracted the prosody and duration information by means of trial-and-error experiments. In this paper, a method is proposed to improve the naturalness in a Test-to-speech using this information. As the results, the Text-to-speech system proposed and implemented in this paper showed more natural speech synthesis than the system, which do not use this information, did.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
Y. J. Seog, K. J. Beom, L. J. Hyun, "Design and Implementation of a Text-to-Speech System using the Prosody and Duration Information," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 3, no. 5, pp. 1121-1129, 1996. DOI: 10.3745/KIPSTE.1996.3.5.1121.

[ACM Style]
Yang Jin Seog, Kim Jae Beom, and Lee Jung Hyun. 1996. Design and Implementation of a Text-to-Speech System using the Prosody and Duration Information. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 3, 5, (1996), 1121-1129. DOI: 10.3745/KIPSTE.1996.3.5.1121.