Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Expressive Prosody for Unit-Selection Speech Synthesis

Volker Strom, Robert A. J. Clark, Simon King

University of Edinburgh, UK

Current unit selection speech synthesis voices cannot produce emphasis or interrogative contours because of a lack of the necessary prosodic variation in the recorded speech database. A method of recording script design is proposed which addresses this shortcoming. Appropriate components were added to the target cost function of the Festival Multisyn engine, and a perceptual evaluation showed a clear preference over the baseline system.

Full Paper

Bibliographic reference.  Strom, Volker / Clark, Robert A. J. / King, Simon (2006): "Expressive prosody for unit-selection speech synthesis", In INTERSPEECH-2006, paper 1522-Tue3BuP.1.