[hts-users:03406] Re: CMU-ARCTIC-SLT demo

[Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>]

Hi,

Demo scripts assume that 1 raw file have 1 utterance.
Therefore, 1 raw file have 1 utterance-level context.
Only the first line of the label is required because only the
utterance-level contexts are used for the context-clustering of GV.

Regards,
Keiichiro Oura


2012/9/25 Fatih Kıralioğlu <fatih.kiralioglu@xxxxxxxxxxxxx>:
> Hi,
> During the generation of global variance in the Training.pl script of
> CMU-ARCTIC-SLT demo, we try to separate silence labels and generate a new
> model without these redundant information. make_data_gv() subroutine
> undertakes this job by generating a list of silences under the file:
> gv\qst001\ver1\gv.list
> What I could not understand is that  the script only generates model for
> silences in the beginning of utterance and silence contexts for the end of
> the utterances is not included in the list. I wonder if there is a
> particular reason for this situation. In the synthesis results using my
> own database, I have observed some explosive distortion at the end of
> utterances and I think there may be a connection between the two.
> Thanks in advance.
> Best Regards.
>