[hts-users:01325] Re: Duration modeling

["Heiga ZEN (Byung Ha CHUN)" <zen@xxxxxxxxxxxxxxx>]

Hi,

bereket kasaye wrote (2008/04/11 3:00):

>  From one of Heiga Zen publications titled "HMM based speech synthesis 
> (HTS) version 2.0 ", I read that state duration PDF's can be generated 
> using HRest with the option -g.  But, when I read the documentation for 
> HTK-3.4 HRest does not use the option -g.
> I do believe  that i missed some concept some where.

This option is added to HRest in HTS, so it does not exist in HTK.
HTKBook is a documentation for HTK, it is useful to understand how to use HTS.
However, there are a number of functions which have been added in HTS.
These functions are not described in HTKBook.

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
------------------------------------------------