Sixth ISCA Workshop on Speech Synthesis

Bonn, Germany
August 22-24, 2007

The HMM-based Speech Synthesis System (HTS) Version 2.0

Heiga Zen (1), Takashi Nose (2), Junichi Yamagishi (2,3), Shinji Sako (1,4), Takashi Masuko (2), Alan W. Black (5), Keiichi Tokuda (1)

(1) Nagoya Institute of Technology, Japan
(2) Tokyo Institute of Technology, Japan
(3) University of Edinburgh, UK
(4) Tokyo University, Japan
(5) Carnegie Mellon University, Pittsburgh, PA, USA

A statistical parametric speech synthesis system based on hidden Markov models (HMMs) has grown in popularity over the last few years. This system simultaneously models spectrum, excitation, and duration of speech using context-dependent HMMs and generates speech waveforms from the HMMs themselves. Since December 2002, we have publicly released an open-source software toolkit named HMM-based speech synthesis system (HTS) to provide a research and development platform for the speech synthesis community. In December 2006, HTS version 2.0 was released. This version includes a number of new features which are useful for both speech synthesis researchers and developers. This paper describes HTS version 2.0 in detail, as well as future release plans.

Full Paper

Bibliographic reference.  Zen, Heiga / Nose, Takashi / Yamagishi, Junichi / Sako, Shinji / Masuko, Takashi / Black, Alan W. / Tokuda, Keiichi (2007): "The HMM-based speech synthesis system (HTS) version 2.0", In SSW6-2007, 294-299.