[hts-users:01101] Re: HTS-2.1beta

[Junichi Yamagishi <jyamagis@xxxxxxxxxxxx>]

Hi,

On 2008/01/15, at 11:13, Sacha Krstulovic wrote:
> Thanks for this release.
>
> 2 questions:
>
> > I'd like to release the beta version of HTS-2.1,  
> > hts_engine_API-0.95, and its demonstrations. [...]
> > http://hts.sp.nitech.ac.jp/archives/2.1beta/HTS-demo_CMU-ARCTIC- 
> > SLT.tar.bz2
> > http://hts.sp.nitech.ac.jp/archives/2.1beta/HTS-demo_CMU-ARCTIC- 
> > ADAPT.tar.bz2
>
> Has anything changed in the demos?
> (Since they do not have a version number, it is difficult
>  to know if they need to be downloaded again.

As Zen wrote in the previous mail, HSMM-based training, adaptation,  
and synthesis are newly supported.
In addition mel-generalized cepstrum, mgc-lsp, semi-tied covariance,  
and so on are included.


> > HTS-2.1beta:
> [...]
> > - Random generation of state transitions, state durations, and  
> > mixture components.
>
> What does this random generation refer to? Initialization
> of the models, or some alternative parameter generation logic?
> Is that described in a particular article?

Probably, there is no particular articles, I guess.

Random generation[sampling] of Gaussian distributions for Trajectory  
HMM (see chapter 5)
http://www.sp.nitech.ac.jp/~zen/english/index.php? 
plugin=attach&refer=Publications%2FInternational% 
20conferences&openfile=tokuda-beyondHMM.pdf
has already supported in the previous version 2.0.

This extension newly supports random sampling of state transitions,  
state durations, and/or
mixture components in the parameter generation algorithm using the  
Trajectory HMMs.

This function would be good when you want to randomly change  
synthesized trajectory or
duration for the synthesized trajectory somewhat every time.

Please imagine human-motion synthesis. If the generated motion  
trajectory is
always completely the same, people would think it is unnatural.
The above function can add some random effect to the generated  
trajectory.