High quality TTS voices within one day

Abstract

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 1day process giving access to high quality TTS voices. 

Topics

4 Figures and Tables

Slides referencing similar topics