[hts-users:03640] Re: v2.2 STRAIGHT demo: MGC2SP usage bug?

[Keiichiro Oura <uratec@xxxxxxxxxxxxxxx>]

Hi,

Please, check HTS-2.3 alpha.
In HTS-2.3 alpha, sp and ap are 1025 float vector sequences as follows.

         printf SYN "sp = fread(fid1,[%d, %d],'float');\n", 1025, $T;
         printf SYN "ap = fread(fid2,[%d, %d],'float');\n", 1025, $T;
         printf SYN "f0 = fread(fid3,[%d, %d],'float');\n", 1,    $T;

Thank you for your report.

Regards,
Keiichiro Oura


2013/2/23 David Klein <dklein@xxxxxxxxxxxx>:
> One more thing, if this is corrected, then the following line also has to be
> corrected:
>
>
>
> printf SYN "sp = fread(fid1,[%d, %d],'float');\n", 513,  $T;
>
>
>
> Here, 513 should be changed to 1025.
>
>
>
> --David
>
>
>
> From: David Klein [mailto:dklein@xxxxxxxxxxxx]
> Sent: Friday, February 22, 2013 3:22 PM
> To: hts-users@xxxxxxxxxxxxxxx
> Subject: [hts-users:03636] v2.2 STRAIGHT demo: MGC2SP usage bug?
>
>
>
> In Training.pl of HTS-demo_CMU-ARCTIC-SLT_STRAIGHT, there is this usage of
> MGC2SP:
>
>
>
> shell( "$MGC2SP -a $fw -g $gm -m " . ( $ordr{'mgc'} - 1 ) . " -l 1024 -o 2
> $mgc > $gendir/$base.sp" );
>
>
>
> The output $base.sp is later read into MATLAB and passed into the STRAIGHT
> synthesis function, along with the corresponding $base.ap and $base.f0.
>
>
>
> I noticed that in MATLAB, the sp and ap data do not have the same size along
> the spectral dimension. Specifically, ap has spectral size 1025 and sp has
> spectral size 513.
>
>
>
> Note that when STRAIGHT is used to generate training data, sp and ap do have
> the same spectral size: 1025. Additionally, when MGCEP and LPC2LSP are used
> to generate training data, they are used with –l 2048 (-n 2048 for LPC2LSP).
>
>
>
> Surprisingly, it seems that the STRAIGHT synthesis is correcting for the
> size mismatch, presumably by interpolating sp up to the correct size. I
> confirmed this with some experimentation.
>
>
>
> Based on all this, I am guessing that MGC2LSP should be used with –l 2048,
> in order to be fully consistent.
>
>
>
> Regards,
>
> David Klein
>
>
>
>