HMM-based Speech Synthesis System (HTS) - Home

Welcome! †

The HMM-based Speech Synthesis System (HTS) has been being developed by the HTS working group and others (see Who we are and Acknowledgments). The training part of HTS has been implemented as a modified version of HTK and released as a form of patch code to HTK. The patch code is released under a free software license. However, it should be noted that once you apply the patch to HTK, you must obey the license of HTK. Related publications about the techniques and algorithms used in HTS can be found here.

HTS version 2.1 includes hidden semi-Markov model (HSMM) training/adaptation/synthesis, speech parameter generation algorithm considering global variance (GV), SMAPLR/CSMAPLR adaptation, and other minor new features. Many bugs in HTS version 2.0.1 were also fixed. The API for runtime synthesis module, hts_engine API, version 1.0 was also released. Because hts_engine can run without the HTK library, users can develop their own open or proprietary softwares based on hts_engine. HTS and hts_engine API does not include any text analyzers but the Festival Speech Synthesis System, DFKI MARY Text-to-Speech System, or other text analyzers can be used with HTS. This distribution includes demo scripts for training speaker-dependent and speaker-adaptive systems using CMU ARCTIC database (English). Six HTS voices for Festival 1.96 are also released. They use the hts_engine module included in Festival. Each of HTS voices can be used without any other HTS tools.

For training Japanese voices, a demo script using the Nitech database is also prepared. Japanese voices trained by the demo script can be used on GalateaTalk, which is a speech synthesis module of an open-source toolkit for anthropomorphic spoken dialogue agents developed in Galatea project. An HTS voice for Galatea trained by the demo script is also released.

News! †

• December 25, 2009

  HTS version 2.1.1 beta was released to the hts-users ML members.

• August 27, 2009

  The first HTS meeting in Interspeech 2009.

• May 22, 2009

  HTS-Demo for Brazilian Portuguese is released.

• March 16, 2009

  Prof. Keiichi Tokuda & Dr. Heiga Zen have a tutorial about HMM-based speech synthesis at Interspeech 2009.