Personal tools
You are here: Home Events ILCC/HCRC Seminar Series Previous speakers Seminar: Heiga Zen

Seminar: Heiga Zen

— filed under:

Statistical parametric speech synthesis by product of experts.

What
  • Seminar
When Mar 11, 2011
from 11:00 AM to 12:30 PM
Where IF-4.31/33
Contact Name
Contact Phone 0131 650 4446
Add event to calendar vCal
iCal

Multiple-level acoustic models (AMs) are often combined in statistical parametric speech synthesis. Both linear and non-linear functions of the observation sequence are used as features in these AMs. This combination of multiple-level AMs can be expressed as a product of experts (PoE); the likelihoods from the AMs are scaled, multiplied together and then normalized. Currently these multiple-level AMs are individually trained and only combined at the synthesis stage.  This seminar discusses a more consistent PoE framework where the AMs are jointly trained. A generalization of trajectory HMM training can be used for multiple-level Gaussian AMs based on linear functions.  However for the non-linear case this is not possible, so a scheme based on contrastive divergence learning is described.

This is joint work with Mark Gales, Yoshihiko Nankaku, and Keiichi Tokuda.

More information about this event…

Document Actions