The Seventh ISCA Tutorial and Research Workshop on Speech Synthesis

Kyoto, Japan
September 22-24, 2010

High Quality TTS Voices Within One Day

Didier Cadic (1), Christophe d'Alessandro (2)

(1) Orange Labs, France; (2) CNRS-LIMSI, France

State-of-the-art unit-selection text-to-speech systems currently produce very natural synthetic speech, at the price however of a costly and time-consuming voice creation process. We report here an extensive perceptual evaluation of several voice creation strategies, and conclude with a novel 1- day process giving access to high quality TTS voices.

Index Terms: speech synthesis, unit selection, vocalic sandwich, script design, rushes, segmentation, evaluation

Full Paper

Bibliographic reference.  Cadic, Didier / d'Alessandro, Christophe (2010): "High quality TTS voices within one day", In SSW7-2010, 288-293.