[hts-users:00953] Re: question about feature extraction

Extracting MGC-LSP coefficients from raw/cmu_us_arctic_slt_a0001.raw
mgcep : Invalid option 'f'!

mgcep - mel-generalized cepstral analysis

usage:
       mgcep [ options ] [ infile ] > stdout
options:
       -a a : alpha                             [0.35]
       -g g : gamma                             [0]
       -m m : order of mel-generalized cepstrum [25]
       -l l : frame length                      [256]
       -o o : output format                     [0]
                 0 (c~0...c~m)
                 1 (b0...bm)
                 2 (K~,c~'1...c~'m)
                 3 (K,b'1...b'm)
                 4 (K~,g*c~'1...g*c~'m)
                 5 (K,g*b'1...g*b'm)
     (level 2)
       -i i : minimum iteration                 [2]
       -j j : maximum iteration                 [30]
       -d d : end condition                     [ 0.001]
       -p p : order of recursions               [l-1]
       -e e : small value added to periodgram   [0]
       -h    : print this message
infile:
       windowed sequence (float)                 [stdin]
stdout:
       mel-generalized cepstrum (float)
notice:
       if g >= 1.0, g = -1 / g

SPTK: version 3.1
CVS Info: $Id: mgcep.c,v 1.19 2007/09/30 16:20:31 heigazen Exp $
Extracting MGC-LSP coefficients from raw/cmu_us_arctic_slt_a0002.raw
mgcep : Invalid option 'f'!

On Nov 19, 2007 5:48 PM, Heiga ZEN (Byung Ha CHUN) < zen@xxxxxxxxxxxxxxx> wrote:

Hi,

Yufeng Hao wrote (2007/11/19 18:20):

> recently, I made some tries on HTS training under version 2.0.1 with my
> cmu arctic like english voice.
>
> Configurations are list below:
> ./configure --with-tcl-search-path=/opt/ActiveTcl- 8.4/bin \
>
> --with-fest-search-path=/home/HMM/festival/festival/examples \
> --with-sptk-search-path=/usr/local/SPTK/bin \
> --with-hts-search-path=/usr/local/bin \
> MGCORDER=12 MGCLSP=1 GAMMA=3 FREQWARP=0.42 LNGAIN=1
>
>
> while feature extracting process, some warning message displays, but I
> can not find related explainings.
> The warning message list as below:
>
> Extracting MGC-LSP coefficients from raw/cmu_us_arctic_slt_a0289.raw
> mgcep : Error in theq() at 0th iteration!
> Extracting MGC-LSP coefficients from raw/cmu_us_arctic_slt_a0290.raw
> Extracting MGC-LSP coefficients from raw/cmu_us_arctic_slt_a0291.raw
> Extracting MGC-LSP coefficients from raw/cmu_us_arctic_slt_a0292.raw
> mgcep : Error in theq() at 0th iteration!
> Extracting MGC-LSP coefficients from raw/cmu_us_arctic_slt_a0293.raw
> Extracting MGC-LSP coefficients from raw/cmu_us_arctic_slt_a0294.raw
>
> Does anybody tell me what happened? Is there any harmful for following
> training?

It means that determinant of Toeplitz+Hankel matrix, which is a coefficient matrix of a linear system in MGC analysis, is too small (< 1.0e-6).
You can modify this threshold via -f option as

mgcep -a 0.42 -g 3 -m 12 -f 0.01 ...

Please run it again with a smaller threshold.

Regards,

--
------------------------------------------------
Heiga ZEN (in Japanese pronunciation)
Byung Ha CHUN (in Korean pronunciation)

Department of Computer Science and Engineering
Nagoya Institute of Technology
Gokiso-cho, Showa-ku, Nagoya 466-8555 Japan

http://www.sp.nitech.ac.jp/~zen
------------------------------------------------