Sixth European Conference on Speech Communication and Technology

Budapest, Hungary
September 5-9, 1999

A Multilingual Text Processing Engine for the PAPAGENO Text-to-Speech Synthesis System

Matej Rojc (1), Janez Stergar (1), Ralph Wilhelm (2), Horst-Udo Hain (2), Martin Holzapfel (2), Bogomir Horvat (1)

(1) Faculty of Electrical Engineering and Computer Science, University of Maribor, Slovenia
(2) SIEMENS AG, Corporate Technology, Munich, Germany

Automatic synthesis of speech from arbitrary text requires two basic operations: linguistic analysis of input text and speech waveform generation. The achieved quality of the second stage very much de-pends on the reliability and richness of information generated in the first stage. In this paper we discuss possibilities and problems of text analysis for multilingual speech synthesis. The language independent approach requires the separation of all the language specific information into the language specific inventory, which is com-posed of different lexica, various dictionaries and lists. The remaining core represents the language independent text-processing engine.

Full Paper (PDF)   Gnu-Zipped Postscript

Additional Image #1 [GIF]
Additional Image #2 [GIF]
Additional Image #3 [GIF]

Bibliographic reference.  Rojc, Matej / Stergar, Janez / Wilhelm, Ralph / Hain, Horst-Udo / Holzapfel, Martin / Horvat, Bogomir (1999): "A multilingual text processing engine for the PAPAGENO text-to-speech synthesis system", In EUROSPEECH'99, 2107-2110.