Name pronunciation in German text-to-speech synthesis

10 years 4 months ago
Name pronunciation in German text-to-speech synthesis
We describe the name analysis and pronunciation component in the German version of the Bell Labs multilingual text-tospeech system. We concentrate on street names because they encompass interesting aspects of geographical and personal names. The system was implemented in the framework of finite-state transducer technology, using linguistic criteria as well as frequency distributions derived from a database. In evaluation experiments, we compared the performances of the generalpurpose text analysis and the name-specific system on training and test materials. The name-specific system significantly outperforms the generic system. The error rates compare favorably with results reported in the research literature. Finally, we discuss areas for future work.
Stefanie Jannedy, Bernd Möbius
Added 01 Nov 2010
Updated 01 Nov 2010
Type Conference
Year 1997
Where ANLP
Authors Stefanie Jannedy, Bernd Möbius
Comments (0)