Blizzard 2007
in conjunction with the
Sixth ISCA Workshop on Speech Synthesis
Bonn, Germany / August 25, 2007

Speaker-Independent HMM-based Speech Synthesis System - HTS-2007 System for the Blizzard Challenge 2007

Junichi Yamagishi (1), Heiga Zen (2), Tomoki Toda (3), Keiichi Tokuda (29

(1) University of Edinburgh, UM; (2) Nagoya Institute of Technology, Japan; (3) Nara Institute of Science and Technology, Japan

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.

Full Paper

Bibliographic reference.  Yamagishi, Junichi / Zen, Heiga / Toda, Tomoki / (29, Keiichi Tokuda (2007): "Speaker-independent HMM-based speech synthesis system - HTS-2007 system for the Blizzard Challenge 2007", In BLZ3-2007, paper 008.