[hts-users:00051] Re: lip synchronization with cmu voices

[Heiga Zen/Byung-Ha Chun <zen@xxxxxxxxxxxxxxxx>]

Hi Nicholas,

Nicholas Volk wrote:

> I'm wondering how extract phoneme boundary times from Festival-based
> CMU_*_HTS-voices for an animated cartoon character.
> The segment boundaries calculated by Festival
> are saved to the temporary lab file which is then processed by the HTS
> engine. However, if I understood correctly the hts_engine contains
> it's own duration model. I'm wondering if it is possible
> to get the segment boundary info from it.

When you set the variable "hts_use_phone_align" to 1,
phoneme duration predicted by Festival is used,
but default setting uses the duration from its own duration model.
So you should use temporary lab file generated by the hts_engine for 
your purpose.

Best regards,

Heiga Zen / Byung-Ha Chun

--
 ------------------------------------------------
  Heiga Zen     (in Japanese pronunciation)
  Byung-Ha Chun (in Korean pronunciation)

  Department of Computer Science and Engineering
  Graduate School of Engineering
  Nagoya Institute of Technology
  Japan

  e-mail: zen@xxxxxxxxxxxxxxxx
     web: http://kt-lab.ics.nitech.ac.jp/~zen
 ------------------------------------------------