[hts-users:00840] Re: Modification of scheme script from hts voices nitech_us_slt_arctic_hts

[Junichi Yamagishi <jyamagis@xxxxxxxxxxxx>]

I guess Festival does not have such functions to generate the scripts.

If your phoneset is *radio* and lexicon is *CMU*, please replace all  
the term
"nitech_us_cmu_slt_hts" in the scheme scripts to e.g.  
"yourown_us_cmu_slt_hts"
using the sed command.

Junichi


On 2007/10/15, at 16:44, Heiga ZEN (Byung Ha CHUN) wrote:

> Hi,
>
> Jan Kocka wrote (2007/10/16 0:29):
>
> > First, thanks for your last answer. I got next question: How did  
> > you get all this scheme scripts in festival voice  
> > nitech_us_cmu_slt_hts ? How I can generate them  on the ground  of  
> > HTS and its data results ? I know how to gerate them by diphone   
> > synthesis, but HTS ?
>
> Sorry, they were originally made by Dr. Alan Black, so I don't know  
> how to generate them.
> But I think it is not difficult because HTS doesn't use most of  
> them: HTS uses utterance structure only.
>
> Regards,
>
> Heiga ZEN (Byung Ha CHUN)
>
> --
> ------------------------------------------------
> Heiga ZEN     (in Japanese pronunciation)
> Byung Ha CHUN (in Korean pronunciation)
>
> Department of Computer Science and Engineering
> Nagoya Institute of Technology
> Gokiso-cho, Showa-ku, Nagoya 466-8555 Japan
>
> http://www.sp.nitech.ac.jp/~zen
> ------------------------------------------------