[hts-users:03372] Re: question about GV Based parameter generation

[Sébastien Le Maguer <Sebastien.Le_maguer@xxxxxxxx>]

Hi,

the decision tree built for the GV uses only utterance questions. In the previous version of HTS you had one disbribution to apply to generate the utterance. In the current version of HTS you have first to select the GV according to the utterance length and then apply it. This means that the algorithm has not changed but there is a previous step which consists to select the best GV to apply (if I'm not mistaken).

Kind regards,
Sébastien Le Maguer


Le 26/06/2012 18:07, soheil khorram a écrit :

Thanks for your answer,

But I guess I have to explain my question.

The algorithm consider that the GV of each parameters is time invariant and is identical for each contexts. But when we train a decision tree for GV distribution, it causes a context dependent distribution and the distribution may be changed in time.

---

From: Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>
To: hts-users <hts-users@xxxxxxxxxxxxxxx>
Cc: uratec <uratec@xxxxxxxxxxxx>
Sent: Tuesday, June 26, 2012 12:20 AM
Subject: [hts-users:03370] Re: question about GV Based parameter generation

Hi,

The algorithm is not changed.
Only model tying structure is changed.

Keiichiro Oura, Yi-Jian Wu, and Keiichi Tokuda,
Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2009,
Blizzard Challenge 2009, 2009-09.

Regards,
Keiichiro Oura


2012/6/26 soheil khorram <soheil_khorram@xxxxxxxxx>:
> Dear all,
>
> I have read the paper titled "A Speech Parameter Generation Algorithm
> Considering Global Variance for HMM-Based Speech Synthesis" and I am
> confused about the GV distribution. According to the paper, the GV
> distribution for each parameter is a single Gaussian, but in the HTS demo a
> decision tree is trained for this parameter.
> I want to know, when a context dependent distribution is used for GV, what
> part of the algorithm will be changed.
> I will be appreciated if there is a useful reference for it.
> Thanks in advance.
>
> Khorram