Speaker-Independent HMM-based Speech Synthesis System
Junichi Yamagishi, Heiga Zen, Tomoki Toda, Keiichi Tokuda · ERA · 2007
This paper describes an HMM-based speech synthesis system developed by the HTS working group for the Blizzard Challenge 2007. To further explore the potential of HMM-based speech synthesis, we incorporate new features in our conventional system which underpin a speaker-independent approach: speaker adaptation techniques; adaptive training for HSMMs; and full covariance modeling using the CSMAPLR transforms.