Browsing by Author "Heiga Zen"

Now showing items 1-3 of 3

An Excitation Model for HMM-Based Speech Synthesis Based on Residual Modeling

Ranniery Maia; Tomoki Toda; Heiga Zen; Yoshihiko Nankaku; Keiichi Tokuda (2007-08)

This paper describes a trainable excitation approach to eliminate the unnaturalness of HMM-based speech synthesizers. During the waveform generation part, mixed excitation is constructed by state-dependent filtering of ...
Improved Average-Voice-based Speech Synthesis Using Gender-Mixed Modeling and a Parameter Generation Algorithm Considering GV

Junichi Yamagishi; Takao Kobayashi; Steve Renals; Simon King; Heiga Zen; Tomoki Toda; Keiichi Tokuda (2007-08)

For constructing a speech synthesis system which can achieve diverse voices, we have been developing a speaker independent approach of HMM-based speech synthesis in which statistical average voice models are adapted to a ...
Speaker-Independent HMM-based Speech Synthesis System: HTS-2007 System for the Blizzard Challenge 2007

Junichi Yamagishi; Heiga Zen; Tomoki Toda; Keiichi Tokuda (2007-08)

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 ...

Now showing items 1-3 of 3

Search DSpace