the decision tree built for the GV uses only utterance questions. In the previous version of HTS you had one disbribution to apply to generate the utterance. In the current version of HTS you have first to select the GV according to the utterance length and then apply it. This means that the algorithm has not changed but there is a previous step which consists to select the best GV to apply (if I'm not mistaken).
Sébastien Le Maguer
Le 26/06/2012 18:07, soheil khorram a écrit :