HMM/DNN-based Speech Synthesis System (HTS) -
Welcome
[
Front page
] [
New
|
Page list
|
Search
|
Recent changes
|
Help
|
Log in
]
Start:
* Welcome! [#k4f3be02]
> The [[HMM/DNN-based Speech Synthesis System (HTS)>http:...
Related publications about the techniques and algorithms ...
found [[here>Publications]].
// 2.3
> HTS version 2.3 includes VBLR speaker adaptation, DAEM-...
Many bugs in HTS version 2.2 were also fixed.
HTS does not include any text analyzers but the [[Festiva...
HTS slides are also released as a tutorial of HMM-based s...
> This distribution includes demo scripts for training sp...
For training other voices, demo scripts using NITech data...
> In addition, HTS version 2.3.1 demo scripts support fra...
// 2.2
//> HTS version 2.2 includes deterministic annealing EM a...
//Many bugs in HTS version 2.1.1 were also fixed.
//HTS does not include any text analyzers but the [[Festi...
//HTS slides are also released as a tutorial of HMM-based...
//> This distribution includes demo scripts for training ...
//For training other voices, demo scripts using Nitech da...
// 2.1.1
//> HTS version 2.1.1 is based on HTK-3.4.1 and includes ...
//Many bugs in HTS version 2.1 were also fixed.
//HTS does not include any text analyzers but the [[Festi...
//This distribution includes demo scripts for training sp...
//> For training Japanese voices, a demo script using the...
// 2.1
//> HTS version 2.1 includes hidden semi-Markov model (HS...
//Six HTS voices for Festival 1.96 are also released. Th...
//> For training Japanese voices, a demo script using the...
* News! [#ve28e7f9]
- ''March 12, 2021''
> The code to train DNN-HSMM for text-to-speech synthesis...
DNN-HSMM maps phoneme(state)-level linguistic features in...
- The code:
-- Supports model training based on a maximum likelihood ...
-- Supports maximum likelihood parameter generation (MLPG).
- ''December 25, 2017''
> HTS version 2.3.2 was released.~
Its new features are
- Demo scripts:
-- Add trajectory training considering global variance ba...
-- Add speaker adaptive training for DNN. (It trains the ...
- ''December 25, 2016''
> HTS version 2.3.1 was released.~
Its new features are
- Demo scripts:
-- Add frame-by-frame modeling option using DNN (deep neu...
- ''December 25, 2015''
> HTS version 2.3 was released.~
Its new features are
- HERest:
-- Add VBLR adaptation.
- HMGenS:
-- Add DAEM-based parameter generation.
-- Support DP search to determine state duration when the...
- HInit, HRest, HRest:
-- Support parallel mode.
- HHEd:
-- Speed up context-clustering by calculating differences...
-- Add untying weights function in HHEd.
- Demo scripts:
-- Add modulation spectrum-based postfilter.
-- Support text files instead of utt files for general En...
-- Turn off spectrum normalization in STRAIGHT.
-- Add LSP postfilter.
-- Support mel-cepstrum based aperiodic measure generated...
-- Support new HTS voice format for hts engine API.
-- Integrate normal demo and STRAIGHT demo.
- ''December 25, 2014''
> HTS version 2.3 beta was released to the hts-users ML m...
- ''May 1, 2013''
> A tutorial about HMM-based speech synthesis was publish...
- ''December 25, 2012''
> HTS version 2.3 alpha was released to the hts-users ML ...
//- ''July 7, 2011''
//> HTS version 2.2 was released.~
//Its new features are
//- HERest:
//-- Support DAEM algorithm in parameter estimation step.
//- HHEd:
//-- Support KLD-based state-mapping and cross-lingual sp...
//-- Context-clustering can be started in the middle of t...
//- HMgeTool:
//-- Add ECD-based MGE traning command, HMgeTool.
//- HSMMAlign:
//-- Add stand-alone HSMM based forced-alignment command,...
//- Demo scripts:
//-- Change sampling frequency from 16kHz to 48kHz.
//-- Support bark critical-band based aperiodic measure.
//-- Change speaker and singer of Brazilian Portuguese an...
//- Slides:
//-- Release slides as a tutorial of HMM-based speech syn...
//- ''March 3, 2011''
//> HTS version 2.2 beta was released to the hts-users ML...
//- ''December 25, 2010''
//> HTS version 2.2 alpha was released to the hts-users M...
//- ''May 14, 2010''
//> HTS version 2.1.1 was was released.~
//Its new features are
//- Based on HTK-3.4.1
//- Many bug fixes
//- HFst:
//-- WFST converter for forced-alignment of HSMM
//- HMGenS:
//-- Initial GV weight for parameter generation
//-- Model-level alignments given from label of singing v...
//- HHEd:
//-- Memory reduction options for context-clustering
//- Demo scripts:
//-- Context-dependent GV without silent and pause phoneme
//-- Demo using the Nitech Japanese database for singing ...
//- ''December 25, 2009''
//> HTS version 2.1.1 beta was released to the hts-users ...
//- ''August 27, 2009''
//> The first HTS meeting in [[Interspeech 2009:http://ww...
//- ''May 22, 2009''
//> HTS-Demo for Brazilian Portuguese is released.
// - ''March 16, 2009''
// > Prof. Keiichi Tokuda & Dr. Heiga Zen have a [[tutori...
//- ''July 31, 2008''
//> The API of runtime synthesis engine, hts_engine API, ...
// hts_engine API version 1.01 and Flite+hts_engine versi...
//- ''July 14, 2008''
//> [[Keiichiro Oura:http://www.sp.nitech.ac.jp/~uratec/]...
//- ''June 27, 2008''
//> HTS version 2.1 and hts_engine API version 1.0 were r...
//Their new features are
//- HTS-2.1
//-- Many bug fixes
//-- Released under the [[New and Simplified BSD //licens...
//-- Simple documentation
//-- 64-bit compile support
//-- MAXSTRLEN (max length of strings), SMAX (max # of st...
// ./configure MAXSTRLEN=1024 SMAX=20
//-- HFB:
//--- HSMM training and adaptation
//-- HAdapt:
//--- SMAPLR/CSMAPLR adaptation
//-- HGen:
//--- Speech parameter generation algorithm considering GV
//--- Random generation of state transitions, state durat...
//-- HMGenS:
//--- Speech parameter generation from HSMMs
//-- HHEd:
//--- Add DM command to delete existing macros
//--- Add IT command to impose pre-built trees in cluster...
//--- Add JM command to merge difference models on state ...
//--- MU command supports '*2' style mixing up
//--- MU command supports mixture-level occupancy thresho...
//- hts_engine API-1.0:
//-- Released under the [[New and Simplified BSD //licens...
//-- Support LSP-type parameters including LSP, mel-LSP, ...
//-- Speech parameter generation algorithm considering GV
//- ''June 13, 2008''
//> HTS version 2.1RC2 and hts_engine API version 0.99 we...
//See [[here:http://hts.sp.nitech.ac.jp/hts-users/spool/2...
// - ''May 27, 2008''
// > HTS voice building tools for the MARY platform was r...
//
// - ''March 24, 2008''
// > HTS version 2.1RC1 and hts_engine API version 0.96 w...
// - ''January 15, 2008''
// > HTS version 2.1beta and hts_engine API version 0.95 ...
// - ''December 7, 2007''
// > hts_engine was ported to Java and included in [[DFKI...
// - ''November 1, 2007''
// > HTS version 2.1alpha was released to the hts-users M...
// - ''October 1, 2007''
// > HTS version 2.0.1 and hts_engine_API version 0.9 wer...
// The new features are
// - Many bug fixes.
// - Band structure for linear transforms.
// - Stream-dependent variance flooring scales.
// - State duration model mmf structure is changed. In t...
// - Demo scripts support LSP-type parameters for spectra...
// - API-style implementation of hts_engine. Old stand-a...
// - ''September 20, 2007''
// > HTS version 2.0.1RC1 was released to the hts-users M...
// - ''September 18, 2007''
// > HTS version 2.0.1RC1 was released to the internal wo...
End:
* Welcome! [#k4f3be02]
> The [[HMM/DNN-based Speech Synthesis System (HTS)>http:...
Related publications about the techniques and algorithms ...
found [[here>Publications]].
// 2.3
> HTS version 2.3 includes VBLR speaker adaptation, DAEM-...
Many bugs in HTS version 2.2 were also fixed.
HTS does not include any text analyzers but the [[Festiva...
HTS slides are also released as a tutorial of HMM-based s...
> This distribution includes demo scripts for training sp...
For training other voices, demo scripts using NITech data...
> In addition, HTS version 2.3.1 demo scripts support fra...
// 2.2
//> HTS version 2.2 includes deterministic annealing EM a...
//Many bugs in HTS version 2.1.1 were also fixed.
//HTS does not include any text analyzers but the [[Festi...
//HTS slides are also released as a tutorial of HMM-based...
//> This distribution includes demo scripts for training ...
//For training other voices, demo scripts using Nitech da...
// 2.1.1
//> HTS version 2.1.1 is based on HTK-3.4.1 and includes ...
//Many bugs in HTS version 2.1 were also fixed.
//HTS does not include any text analyzers but the [[Festi...
//This distribution includes demo scripts for training sp...
//> For training Japanese voices, a demo script using the...
// 2.1
//> HTS version 2.1 includes hidden semi-Markov model (HS...
//Six HTS voices for Festival 1.96 are also released. Th...
//> For training Japanese voices, a demo script using the...
* News! [#ve28e7f9]
- ''March 12, 2021''
> The code to train DNN-HSMM for text-to-speech synthesis...
DNN-HSMM maps phoneme(state)-level linguistic features in...
- The code:
-- Supports model training based on a maximum likelihood ...
-- Supports maximum likelihood parameter generation (MLPG).
- ''December 25, 2017''
> HTS version 2.3.2 was released.~
Its new features are
- Demo scripts:
-- Add trajectory training considering global variance ba...
-- Add speaker adaptive training for DNN. (It trains the ...
- ''December 25, 2016''
> HTS version 2.3.1 was released.~
Its new features are
- Demo scripts:
-- Add frame-by-frame modeling option using DNN (deep neu...
- ''December 25, 2015''
> HTS version 2.3 was released.~
Its new features are
- HERest:
-- Add VBLR adaptation.
- HMGenS:
-- Add DAEM-based parameter generation.
-- Support DP search to determine state duration when the...
- HInit, HRest, HRest:
-- Support parallel mode.
- HHEd:
-- Speed up context-clustering by calculating differences...
-- Add untying weights function in HHEd.
- Demo scripts:
-- Add modulation spectrum-based postfilter.
-- Support text files instead of utt files for general En...
-- Turn off spectrum normalization in STRAIGHT.
-- Add LSP postfilter.
-- Support mel-cepstrum based aperiodic measure generated...
-- Support new HTS voice format for hts engine API.
-- Integrate normal demo and STRAIGHT demo.
- ''December 25, 2014''
> HTS version 2.3 beta was released to the hts-users ML m...
- ''May 1, 2013''
> A tutorial about HMM-based speech synthesis was publish...
- ''December 25, 2012''
> HTS version 2.3 alpha was released to the hts-users ML ...
//- ''July 7, 2011''
//> HTS version 2.2 was released.~
//Its new features are
//- HERest:
//-- Support DAEM algorithm in parameter estimation step.
//- HHEd:
//-- Support KLD-based state-mapping and cross-lingual sp...
//-- Context-clustering can be started in the middle of t...
//- HMgeTool:
//-- Add ECD-based MGE traning command, HMgeTool.
//- HSMMAlign:
//-- Add stand-alone HSMM based forced-alignment command,...
//- Demo scripts:
//-- Change sampling frequency from 16kHz to 48kHz.
//-- Support bark critical-band based aperiodic measure.
//-- Change speaker and singer of Brazilian Portuguese an...
//- Slides:
//-- Release slides as a tutorial of HMM-based speech syn...
//- ''March 3, 2011''
//> HTS version 2.2 beta was released to the hts-users ML...
//- ''December 25, 2010''
//> HTS version 2.2 alpha was released to the hts-users M...
//- ''May 14, 2010''
//> HTS version 2.1.1 was was released.~
//Its new features are
//- Based on HTK-3.4.1
//- Many bug fixes
//- HFst:
//-- WFST converter for forced-alignment of HSMM
//- HMGenS:
//-- Initial GV weight for parameter generation
//-- Model-level alignments given from label of singing v...
//- HHEd:
//-- Memory reduction options for context-clustering
//- Demo scripts:
//-- Context-dependent GV without silent and pause phoneme
//-- Demo using the Nitech Japanese database for singing ...
//- ''December 25, 2009''
//> HTS version 2.1.1 beta was released to the hts-users ...
//- ''August 27, 2009''
//> The first HTS meeting in [[Interspeech 2009:http://ww...
//- ''May 22, 2009''
//> HTS-Demo for Brazilian Portuguese is released.
// - ''March 16, 2009''
// > Prof. Keiichi Tokuda & Dr. Heiga Zen have a [[tutori...
//- ''July 31, 2008''
//> The API of runtime synthesis engine, hts_engine API, ...
// hts_engine API version 1.01 and Flite+hts_engine versi...
//- ''July 14, 2008''
//> [[Keiichiro Oura:http://www.sp.nitech.ac.jp/~uratec/]...
//- ''June 27, 2008''
//> HTS version 2.1 and hts_engine API version 1.0 were r...
//Their new features are
//- HTS-2.1
//-- Many bug fixes
//-- Released under the [[New and Simplified BSD //licens...
//-- Simple documentation
//-- 64-bit compile support
//-- MAXSTRLEN (max length of strings), SMAX (max # of st...
// ./configure MAXSTRLEN=1024 SMAX=20
//-- HFB:
//--- HSMM training and adaptation
//-- HAdapt:
//--- SMAPLR/CSMAPLR adaptation
//-- HGen:
//--- Speech parameter generation algorithm considering GV
//--- Random generation of state transitions, state durat...
//-- HMGenS:
//--- Speech parameter generation from HSMMs
//-- HHEd:
//--- Add DM command to delete existing macros
//--- Add IT command to impose pre-built trees in cluster...
//--- Add JM command to merge difference models on state ...
//--- MU command supports '*2' style mixing up
//--- MU command supports mixture-level occupancy thresho...
//- hts_engine API-1.0:
//-- Released under the [[New and Simplified BSD //licens...
//-- Support LSP-type parameters including LSP, mel-LSP, ...
//-- Speech parameter generation algorithm considering GV
//- ''June 13, 2008''
//> HTS version 2.1RC2 and hts_engine API version 0.99 we...
//See [[here:http://hts.sp.nitech.ac.jp/hts-users/spool/2...
// - ''May 27, 2008''
// > HTS voice building tools for the MARY platform was r...
//
// - ''March 24, 2008''
// > HTS version 2.1RC1 and hts_engine API version 0.96 w...
// - ''January 15, 2008''
// > HTS version 2.1beta and hts_engine API version 0.95 ...
// - ''December 7, 2007''
// > hts_engine was ported to Java and included in [[DFKI...
// - ''November 1, 2007''
// > HTS version 2.1alpha was released to the hts-users M...
// - ''October 1, 2007''
// > HTS version 2.0.1 and hts_engine_API version 0.9 wer...
// The new features are
// - Many bug fixes.
// - Band structure for linear transforms.
// - Stream-dependent variance flooring scales.
// - State duration model mmf structure is changed. In t...
// - Demo scripts support LSP-type parameters for spectra...
// - API-style implementation of hts_engine. Old stand-a...
// - ''September 20, 2007''
// > HTS version 2.0.1RC1 was released to the hts-users M...
// - ''September 18, 2007''
// > HTS version 2.0.1RC1 was released to the internal wo...
Page:
![[PukiWiki]](skin/logo.png "[PukiWiki]"){kind=logo}
