History source of History(No. 6) - HMM/DNN-based speech synthesis system (HTS)

* History [#af7558b8]
#contents
** 2006 [#z5d7dda6]
>''December 29:''
>> HTS version 2.0 was '''finally''' released :-)~
The new features are
- Based on [[HTK-3.4>http://htk.eng.cam.ac.uk/download.shtml]]
- Compilation without [[SPTK>http://kt-lab.ics.nitech.ac.jp/~tokuda/SPTK/index.html]]
- Thousands of fixed bugs
- HCompV accumulates statistics for variance flooring in double precision
- HRest can generate state duration densities (-g option)
- Model boundaries can be given to HERest (-e option)~
We may specify a part of model boundaries (e.g, pause positions)
- Reduced-memory implementation of context clustering in HHEd (-r option)
- Each decision tree can have a name with regular expression (-p option)~
 TB 000 {(*-a+*, *-i+*, *-u+*).state[2]}
 TB 000 {(*-sil+*, *-pau+*).state[3]}
As a result, deferent two trees can be constructed for consonants and vowels, respectively.
- The interface of HMGenS has been switched from ''HHEd-style'' to ''HERest-style''
- Flexible model structures in HMGenS (in the previous version, the first stream is assumed as mcep, and the others are assumed as log f0).  Non-left-to-right models and full covariance matrices for state output pdfs can also be used.
- EM-based parameter generation algorithm (-c option), i.e, mixture of Gaussians can be used. 
 -c 0: Cholesky decomposition
 -c 1: EM (with fixed state sequence)
 -c 2: EM (phone boundaries can be given with -e option)
- Speaker adaptation, adaptive training, and semi-tied covariance transforms are supported for multi-stream HMMs/MSD-HMMs. 
-- MLLR (MLLRMEAN, MLLRCOV, CMLLR) adaptation.
-- SAT (CMLLR) is also supported.
-- Decision trees for context clustering can be used for definition of regression classes for adaptation.
-- HMGenS can read regression matrices for adaptation.
- MAP adaptation is also supported.
- hts_engine 
- miscellaneous changes.

>''December 4:''
>> HTS version 2.0RC3 was released to members of Mailing List.
>''July 1:''
>> HTS version 2.0RC2 was released to members of Mailing List.
>''March 3:''
>> HTS version 2.0RC1 was released to members of Mailing List.
>''February 15:''
>> HTS version 2.0RC0 was released to the internal working group. 

** 2003 [#ld26312a]
>''December 26:''
>> HTS version 1.1.1 was released. The new features were
- Based on HTK-3.2.1
- Demo script for ARCTIC database
- Demo script for an original database (Japanese)
- Variance flooring in demo script
- Postfiltering in hts-engine
- Many fixed bugs

>''Oct. 14:''
>> New HTS voices trained by ARCTIC databases were released. 
>''June 11:''
>>  HTS version 1.1b was released.
>''May 9:''
>> HTS version 1.1 was released. The new features were
- A small synthesis engine (to be called from Festival).
- HMM file format converter for the engine.
- Many fixed bugs (Thanks for reporting them).
- Accompanied by HTS voices for Festival.

>''January 21:''
>> Minor revision was made to HTS version 1.0. 

** 2002 [#s0e2a8a8]
>''December 25:''
>> HTS version 1.0 was released.
//>''September:''
//>> The first paper about eigenvoice for HMM-based speech synthesis was //appeared in ICSLP'02.
//
//** 1999 [#v67c04e5]
//> ''September:''
//>> The first paper about the current HTS framework was appeared in //Eurospeech'99. 
//> ''March:''
//>> The first paper about MSD-HMM was appeared in ICASSP'99.
//
//** 1998 [#v760e959]
//> ''November:''
//>> The first paper about speaker adaptation for the HMM-based speech synthesis //using MLLR was appeared in ESCA/COCOSDA workshop on speech synthesis.
//
//** 1997 [#v95967aa]
//> ''September:''
//>> The first paper about speaker interpolation for the HMM-based speech //synthesis was appeared in Eurospeech'97.
//
** 1995 [#v5285cba]
> ''May:''
>> The first paper about the speech parameter generation algorithm was appeared  in ICASSP'95.
HMM/DNN-based Speech Synthesis System (HTS) - History source of History (No. 6)
