[hts-users:00689] Re: HTS Training

[Carlos Mendes <cmdm@xxxxxxxxxxxxxxx>]

Thanks for the help Heiga and Alexis,

About the context dependent trees.... yes... I didn't explained myself 
clear .... or maybe I'm not seeing this correctly, :), I'm relatively new to 
HMM based synthesis, soo sorry if I'm saying something really stupid. But as 
I see it .... usually units are clustered according to their context 
information, generally according to their placement in the phrase, word, 
syllable, triphone, diphone etc... and other signal features like mcep, 
etc....(at least in unit selection algorithms) depends on what you want. In 
HMM synthesis, HMM's are similarly clustered in context trees ...  
correct...?
I would like to do some analysis on the units that are being used on the 
training, meaning their information relative to the assigned cluster or node. 
For this, I need to know were exactly HTK placed a certain unit, during the 
training....
I could use the questions file and then apply it to the corpus, but I would 
rather prefer to use the information that HTK can give me. Soo the question 
would be .... Is it possible to obtain this information during the training?

thanks again,
Carlos Mendes

On Tuesday 29 May 2007 00:27, Heiga ZEN (Byung Ha CHUN) wrote:
> Hi,
>
> Carlos Mendes wrote (2007/05/29 2:20):
> > 1. During the training is it possible to obtain, from the context
> > dependent trees, information on were a certain segment(monophone) was
> > placed on the tree? Can I do it with HHed or theres another away?
>
> Sorry, I cannot understand your question.
> Can you please explain it in detail?
>
> > 2. Is it possible to increase the number of dimensions of "log f0" and
> > its respective dynamic features? if not, would I have to change htk a
> > lot, or would it be better to insert them as new "features".
>
> Yes, you can increase the dimensionality of "log f0" (MSD) without any
> modifications.
>
> Regards,
>
> Heiga ZEN (Byung Ha CHUN)