HMM/DNN-based Speech Synthesis System (HTS) - Acknowledgments

Acknowledgments †

The following people and related organizations have contributed to the development of HTS in various ways. It is their work that makes it all possible. In no special order:

• Keiichi Tokuda (produce and design)
  Overall concept and design.

• Keiichiro Oura (design and development, main maintainer)
  Implementation of hts_engine API and HSMMAlign. Testing out the version 2.0.1, 2.1, 2.1.1, 2.2, and 2.3. He is the current maintainer of HTS.

Since HTS-2.3.1 †

• Kei Sawada (current member)
• Takenori Yoshimura (current member)

Since HTS-2.3 †

• Shinji Takaki (current member)

Since HTS-2.2 †

• Sayaka Shiota (ex. member)
  Making of HTS Slides.

Since HTS-2.1.1 †

• Kei Hashimoto (current member)

Since HTS-2.0.1 †

• Tomoki Toda (current member)
  Discussions and implementation of GV-based parameter generation algorithms.

Since HTS-2.0 †

• Takashi Nose (current member)
  Testing out the version 2.0.

Since HTS-1.0 †

• Heiga Zen (current member)
  Throwing away all old codes of HTS and rewriting them as HTS version 1.0, 1.1, 1.1b, 1.1.1, 2.0, 2.0.1, and 2.1.

• Junichi Yamagishi (current member)
  Testing out various clustering and adaptation algorithms. Implementation of the CSMAPLR adaptation algorithm.

• Takayoshi Yoshimura (ex. member)
  Development of the first version of HTS.

• Masatsune Tamura (ex. member)
  Implementation of various speaker adaptation algorithms for HMM-based speech synthesis.

• Shinji Sako (current member)
  Applying HMM-based speech synthesis to audio-visual speech.

• Noboru Miyazaki
  Implementation of the first version of MSD-HMM trainer for pitch pattern modeling.

• Tetsuya Yamada
  Testing out various HMM training algorithms for HMM-based speech synthesis.

• Takashi Masuko (ex. member)
  Discussions in detail and implementing speech parameter generation algorithms.

• Takao Kobayashi
  Discussions and supervising students working on speech synthesis.

• Tadashi Kitamura
  Discussions and supervising students working on speech synthesis.

• Satoshi Imai
  Supervising students working on speech synthesis.

• Alan Black (current member)
  Discussions about all aspects of speech synthesis, helping us to use Festival, and supplying speech databases.

Special thanks †

• Steve Young, Phil Woodland, Mark Gales, Gunnar Evermann, and other HTK developers
  Development of HTK.

and many other important contributors (we had to leave them out since they are too many).