Fourth ISCA ITRW on Speech Synthesis
August 29 - September 1, 2001
Close shadowing experiments involving natural and synthetic stimuli are here described. Preliminary results show that speakers are able to follow natural stimuli with an average delay less than 59 ms whereas this delay exceeds 199 ms for stimuli produced by text-to-speech systems. A complementary experiment shows that this contrast is mainly due to prosody.
Bibliographic reference. Bailly, Gérard (2001): "Close shadowing natural vs. synthetic speech", In SSW4-2001, paper 107.