[hts-users:03690] Re:

My guess, the situation is, the distributions estimated by DAEM and EM are obviously different.
That leads to a concrete fact that the derived decision trees have different amounts of leaf nodes.
So the resulting models are of different size, and that's normal.

Xingyu Na (那兴宇)
http://www.idiap.ch/~xna/

At 2013-04-03 11:26:58,"Nirmesh Shah" <supernirmesh@xxxxxxxxx> wrote:

Dear Sir,
      voices/dur.pdf:         data
     voices/gv-lf0.pdf:      data
voices/gv-mgc.pdf:      data
voices/gv-switch.inf:   ASCII text
voices/lf0.pdf:         data
voices/lf0.win1:        ASCII text
voices/lf0.win2:        ASCII text
voices/lf0.win3:        ASCII text
voices/lpf.pdf:         data
voices/lpf.win1:        ASCII text
voices/mgc.pdf:         data
voices/mgc.win1:        ASCII text
voices/mgc.win2:        ASCII text
voices/mgc.win3:        ASCII text
voices/tree-dur.inf:    ASCII text, with very long lines
voices/tree-gv-lf0.inf: ASCII text
voices/tree-gv-mgc.inf: ASCII text
voices/tree-lf0.inf:    ASCII text, with very long lines
voices/tree-lpf.inf:    ASCII text
voices/tree-mgc.inf:    ASCII text, with very long lines

In stats folder in cmp.stats file I got 25431 raws, is it displaying nLeaves?

On Tue, Apr 2, 2013 at 10:20 PM, Sebastien Le Maguer <Sebastien.Le_maguer@xxxxxxxx> wrote:

Hello,

to check this, you only have to use the "file" command if you are on Unix but, according to the size
you have indicated in another mail, I think that you have binary files. Have you checked the number
of leaves in the clustering trees ?

Best regards,
Sébastien Le Maguer
At Tue, 2 Apr 2013 21:30:49 +0530,
Nirmesh Shah wrote:
>
> [1 <text/plain; GB2312 (quoted-printable)>]
>
> [2 <text/html; GB2312 (quoted-printable)>]
> I don't know I am novice. Can you please tell me how to see it?
>
> On Tue, Apr 2, 2013 at 1:02 PM, 那兴宇 <nxy-yzqs@xxxxxxx> wrote:
>
> Did you save the model in binary mode or text mode?
>
> --
> Xingyu Na (那兴宇)
> http://www.idiap.ch/~xna/
>
> At 2013-04-02 14:40:55,"Nirmesh Shah" <supernirmesh@xxxxxxxxx> wrote:
>
> Hello,
> After system building in our language for same hour of durations with EM and DAEM algorithm we
> observed that size of DAEM is less compared to size of EM.
>
> Can you please tell me is there any specific reason of it?
>
> On Tue, Feb 19, 2013 at 7:04 AM, Keiichiro Oura <uratec@xxxxxxxxxxxxxxx> wrote:
>
> Hi,
>
> It's depend on database.
>
> Regards,
> Keiichiro Oura
>
> 2013/2/19 Nirmesh Shah <supernirmesh@xxxxxxxxx>:
> > Hello,
> > So is it 10 is enough? or more you should prefer?
> > Regards,
> > Nirmesh Shah
> >
> >
> > On Mon, Feb 18, 2013 at 8:07 PM, Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>
> > wrote:
> >>
> >> Hi,
> >>
> >> > So I change DAEMNITER=5 So is it going to affect DAEM algorithm(due to
> >> > less
> >> > no of iteration)?
> >>
> >> Number of iteration affect the quality of the synthesized speech.
> >>
> >> > and this DAEM algorithm, Does it work for log F0 re-estimation also in
> >> > system?
> >>
> >> Yes.
> >> Spectrum (mel-cep), pitch (log F0), and duration are estimated in
> >> HERest simultaneously.
> >>
> >> Regards,
> >> Keiichiro Oura
> >>
> >>
> >> 2013/2/18 Nirmesh Shah <supernirmesh@xxxxxxxxx>:
> >> > Dear Sir,
> >> > While making monophone model with the use of DAEM algorithm, It
> >> > is
> >> > taking so much time because DAEMNITER=10 and NITER=5, So at the
> >> > execution of
> >> > HERest re-estimation is done for 50 times as it is having structure like
> >> > this,
> >> >
> >> > if ($daem) {
> >> > for ( $i = 1 ; $i <= $daem_nIte ; $i++ ) {
> >> > for ( $j = 1 ; $j <= $nIte ; $j++ ) {
> >> >
> >> > # embedded reestimation
> >> > $k = $j + ( $i - 1 ) * $nIte;
> >> > print("\n\nIteration $k of Embedded Re-estimation\n");
> >> > $k = ( $i / $daem_nIte )**$daem_alpha;
> >> > shell("$HERest{'mon'} -k $k -H $monommf{'cmp'} -N
> >> > $monommf{'dur'} -M $model{'cmp'} -R $model{'dur'} $lst{'mon'}
> >> > $lst{'mon'}");
> >> > }
> >> > }
> >> > }
> >> > So I change DAEMNITER=5 So is it going to affect DAEM algorithm(due to
> >> > less
> >> > no of iteration)?
> >> > and this DAEM algorithm, Does it work for log F0 re-estimation also in
> >> > system?
> >> > Thanks in advance
> >> >
> >> > Regards,
> >> > Nirmesh Shah
> >> >
> >> > On Fri, Jan 11, 2013 at 4:50 PM, Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>
> >> > wrote:
> >> >>
> >> >> Hi,
> >> >>
> >> >> Yes.
> >> >> Default setting is EM algorithm.
> >> >>
> >> >> The other options can be shown by
> >> >>
> >> >> ./configure --help
> >> >>
> >> >> Regards,
> >> >> Keiichiro Oura
> >> >>
> >> >>
> >> >> 2013/1/11 Nirmesh Shah <supernirmesh@xxxxxxxxx>:
> >> >> > Thanks,
> >> >> > If I don't write it then does it mean that EM algorithm is used?
> >> >> >
> >> >> >
> >> >> > On Fri, Jan 11, 2013 at 2:04 PM, Keiichiro Oura
> >> >> > <uratec@xxxxxxxxxxxxxxx>
> >> >> > wrote:
> >> >> >>
> >> >> >> Hi,
> >> >> >>
> >> >> >> You can try DAEM training in the HTS demo script by following
> >> >> >> command
> >> >> >> line.
> >> >> >> ./configure DAEM=1
> >> >> >>
> >> >> >> Regards,
> >> >> >> Keiichiro Oura
> >> >> >>
> >> >> >>
> >> >> >> 2013/1/11 Nirmesh Shah <supernirmesh@xxxxxxxxx>:
> >> >> >> > Hello,
> >> >> >> > I want to know how to use DAEM algorithm in hts,as I have seen
> >> >> >> > on
> >> >> >> > hts
> >> >> >> > website that HERest command support DAEM, does it mean whenever I
> >> >> >> > use
> >> >> >> > that
> >> >> >> > command ,Is it going to use DAEM algorithm for re-estimation? and
> >> >> >> > what
> >> >> >> > if I
> >> >> >> > don' want to use DAEM?
> >> >> >> >
> >> >> >> > --
> >> >> >> > Thanks & Regards,
> >> >> >> > Nirmesh J. Shah
> >> >>
> >> >> >>
> >> >> >
> >> >> >
> >> >> >
> >> >> > --
> >> >> > Thanks & Regards,
> >> >> > Nirmesh J. Shah
> >> >>
> >> >>
> >> >
> >> >
> >> >
> >> > --
> >> > Thanks & Regards,
> >> > Nirmesh J. Shah
> >> >
> >>
> >
> >
> >
> > --
> > Thanks & Regards,
> > Nirmesh J. Shah
>
> --
> Thanks & Regards,
> Nirmesh J. Shah
>
> --
> Thanks & Regards,
> Nirmesh J. Shah
> M.Tech ( ICT)
>
>

--
Thanks & Regards,
Nirmesh J. Shah
M.Tech ( ICT)