[Subject Prev][Subject Next][Thread Prev][Thread Next][Date Index][Thread Index]

[hts-users:01854] Re: HTS-demo_CMU-ARCTIC-SLT


Solved changed mglsadf -g to -c and -w in sox to -2 but the question is am i forced to rerun the make command again after changing Training.pl
Thanks in Advanced
Mohamed A. Saeed

Date: Fri, 2 Jan 2009 17:23:29 +0000
From: eng.yamany@xxxxxxxxxxx
Subject: [hts-users:01853] Re: HTS-demo_CMU-ARCTIC-SLT
To: hts-users@xxxxxxxxxxxxxxx

I used the command tail and these were the last line what is the problem
ge = 0.002044
   Iteration 50: GV Obj = 2.601513e+03 (HMM:2.601513e+03 GV:-1.473440e-04)  Chan
ge = -0.000241
   Optimization stopped by reaching max # of iterations (50).
Generation complete - average log prob per frame = 1.254381e+02 (64397 frames)
HTK Configuration Parameters[22]
  Module/Tool     Parameter                  Value
                  OPTKIND                   NEWTON
                  GVWEIGHT                       1
                  HMMWEIGHT                      1
                  STEPDEC                 0.500000
                  STEPINC                 1.200000
                  STEPINIT                       1
                  MINEUCNORM              0.010000
                  GVEPSILON               0.000100
                  MAXGVITER                     50
                  GVHMMLIST       /home/Mohamed/htk/HTS-demo_CMU-ARCTIC-SLT/HTS-
demo_CMU-ARCTIC-SLT/models/qst001/ver1/cmp/gv.list
                  GVMODELMMF      /home/Mohamed/htk/HTS-demo_CMU-ARCTIC-SLT/HTS-
demo_CMU-ARCTIC-SLT/models/qst001/ver1/cmp/gv.mmf
                  USEGV                       TRUE
                  EMEPSILON               0.000100
                  MAXEMITER                     20
                  WINDIR          /home/Mohamed/htk/HTS-demo_CMU-ARCTIC-SLT/HTS-
demo_CMU-ARCTIC-SLT/data/win
                  WINFN           StrVec 3 mgc.win1 mgc.win2 mgc.win3 StrVec 3 l
f0.win1 lf0.win2 lf0.win3
                  PDFSTREXT       StrVec 2 mgc lf0
                  PDFSTRORDER        IntVec 2 25 1
                  PDFSTRSIZE          IntVec 2 1 3
                  USEALIGN                    TRUE
                  NATURALWRITEORDER              TRUE
                  NATURALREADORDER              TRUE

=====================================================================
Start synthesizing waveforms (1mix) at Fri Jan  2 07:59:14 EST 2009
=====================================================================
Processing directory /home/Mohamed/htk/HTS-demo_CMU-ARCTIC-SLT/HTS-demo_CMU-ARCT
IC-SLT/gen/qst001/ver1/1mix/0:
 Synthesizing a speech waveform from alice01.mgc and alice01.lf0...mglsadf : Inv
alid option 'g'!
 mglsadf - MGLSA digital filter for speech synthesis
  usage:
       mglsadf [ options ] mgcfile [ infile ] > stdout
  options:
       -m m  : order of mel-generalized cepstrum [25]
       -a a  : alpha                             [0.35]
       -c c  : gamma = -1 / (int) c              [1]
       -p p  : frame period                      [100]
       -i i  : interpolation period              [1]
       -t    : transpose filter                  [FALSE]
       -k    : filtering without gain            [FALSE]
       -P P  : order of Pade approximation       [4]
       -h    : print this message
  infile:
       filter input (float)                      [stdin]
  stdout:
       filter output (float)
  mgcfile:
       mel-generalized cepstrum (float)
  notice:
       if c==0, MLSA filter is used, P should be 4 or 5
 SPTK: version 3.2
 CVS Info: $Id: mglsadf.c,v 1.23 2008/11/06 15:40:51 tatsuyaito Exp $
/bin/sox-14.2.0/sox-14.2.0/sox: invalid option -- w
Failed: invalid option
/bin/sox-14.2.0/sox-14.2.0/sox: SoX v14.2.0
Usage summary: [gopts] [[fopts] infile]... [fopts] outfile [effect [effopts]]...

SPECIAL FILENAMES (infile, outfile):
-                        Pipe/redirect input/output (stdin/stdout); use with -t
-d, --default-device     Use the default audio device (where available)
-n, --null               Use the `null' file handler; e.g. with synth effect
-p, --sox-pipe           Alias for `-t sox -'
SPECIAL FILENAMES (infile only):
"|program [options] ..." Pipe input from external program (where supported)
http://server/file       Use the given URL as input file (where supported)
GLOBAL OPTIONS (gopts) (can be specified at any point before the first effect):
--buffer BYTES           Set the size of all processing buffers (default 8192)
--combine concatenate    Concatenate multiple input files (default for sox, rec)
--combine sequence       Sequence multiple input files (default for play)
--effects-file FILENAME  File containing effects and options
-h, --help               Display version number and usage information
--help-effect NAME       Show usage of effect NAME, or NAME=all for all
--help-format NAME       Show info on format NAME, or NAME=all for all
--input-buffer BYTES     Override the input buffer size (default: as --buffer)
--interactive            Prompt to overwrite output file
-m, --combine mix        Mix multiple input files (instead of concatenating)
-M, --combine merge      Merge multiple input files (instead of concatenating)
--plot gnuplot|octave    Generate script to plot response of filter effect
-q, --no-show-progress   Run in quiet mode; opposite of -S
--replay-gain track|album|off  Default: off (sox, rec), track (play)
-R                       Use default random numbers (same on each run of SoX)
-S, --show-progress      Display progress while processing audio data
--version                Display version number of SoX and exit
-V[LEVEL]                Increment or set verbosity level (default 2); levels:
                           1: failure messages
                           2: warnings
                           3: details of processing
                           4-6: increasing levels of debug messages
FORMAT OPTIONS (fopts):
Input file format options need only be supplied for files that are headerless.
Output files will have the same format as the input file where possible and not
overriden by any of various means including providing output format options.
-v|--volume FACTOR       Input file volume adjustment factor (real number)
-t|--type FILETYPE       File type of audio
-s/-u/-f/-U/-A/-i/-a/-g  Encoding type=signed-integer/unsigned-integer/floating-
                         point/mu-law/a-law/ima-adpcm/ms-adpcm/gsm-full-rate
-e|--encoding ENCODING   Set encoding (ENCODING in above list)
-b|--bits BITS           Encoded sample size in bits
-1/-2/-3/-4/-8           Encoded sample size in bytes
-N|--reverse-nibbles     Encoded nibble-order
-X|--reverse-bits        Encoded bit-order
--endian little|big|swap Encoded byte-order; swap means opposite to default
-L/-B/-x                 Short options for the above
-c|--channels CHANNELS   Number of channels of audio data; e.g. 2 = stereo
-r|--rate RATE           Sample rate of audio
-C|--compression FACTOR  Compression factor for output format
--add-comment TEXT       Append output file comment
--comment TEXT           Specify comment text for the output file
--comment-file FILENAME  File containing comment text for the output file
AUDIO FILE FORMATS: 8svx aif aifc aiff aiffc al amb au avr caf cdda cdr cvs cvsd
 cvu dat dvms f4 f8 fap flac fssd gsm hcom htk ima ircam la lpc lpc10 lu mat mat
4 mat5 maud nist ogg paf prc pvf raw s1 s2 s3 s4 sb sd2 sds sf sl smp snd sndfil
e sndr sndt sou sox sph sw txw u1 u2 u3 u4 ub ul uw vms voc vorbis vox w64 wav w
avpcm wv wve xa xi
PLAYLIST FORMATS: m3u pls
AUDIO DEVICE DRIVERS: oss ossdsp
EFFECTS: allpass band bandpass bandreject bass bend chorus compand contrast dcsh
ift deemph delay dither earwax echo echos equalizer fade filter flanger gain hig
hpass loudness lowpass mcompand mixer noiseprof noisered norm oops pad phaser pi
tch rate remix repeat reverb reverse riaa silence spectrogram speed splice stat
stretch swap synth tempo treble tremolo trim vol
EFFECT OPTIONS (effopts): effect dependent; see --help-effect
Error in /usr/local/SPTK/bin/excite -p 80 /home/Mohamed/htk/HTS-demo_CMU-ARCTIC-
SLT/HTS-demo_CMU-ARCTIC-SLT/gen/qst001/ver1/1mix/0/alice01.pit | /usr/local/SPTK
/bin/mglsadf -m 24 -p 80 -a 0.42 -g 0 /home/Mohamed/htk/HTS-demo_CMU-ARCTIC-SLT/
HTS-demo_CMU-ARCTIC-SLT/gen/qst001/ver1/1mix/0/alice01.mgc | /usr/local/SPTK/bin
/x2x +fs | /bin/sox-14.2.0/sox-14.2.0/sox -c 1 -s -w -t raw -r 16000 - -c 1 -s -
w -t wav -r 16000 /home/Mohamed/htk/HTS-demo_CMU-ARCTIC-SLT/HTS-demo_CMU-ARCTIC-
SLT/gen/qst001/ver1/1mix/0/alice01.wav





Date: Wed, 31 Dec 2008 19:32:57 +0000
From: eng.yamany@xxxxxxxxxxx
Subject: [hts-users:01852] HTS-demo_CMU-ARCTIC-SLT
To: hts-users@xxxxxxxxxxxxxxx

Dear all,
first of all Happy new year and I thank Dr. Sacha for directing me to HTS-demo_CMU-ARCTIC-SLT.
Now I have installed the demo and no errors has occurred. How can I synthesis speech from text.  I mean how can I use the demo and run it.
Is there a way likefestival SayText
Thanks in Advance
best regards
Mohamed A.




check out the rest of the Windows Live™. More than mail–Windows Live™ goes way beyond your inbox. More than messages


check out the rest of the Windows Live™. More than mail–Windows Live™ goes way beyond your inbox. More than messages

Invite your mail contacts to join your friends list with Windows Live Spaces. It's easy! Try it!

Follow-Ups
[hts-users:01855] Re: HTS-demo_CMU-ARCTIC-SLT, Nicholas Volk
References
[hts-users:01852] HTS-demo_CMU-ARCTIC-SLT, Mohamed Abdou
[hts-users:01853] Re: HTS-demo_CMU-ARCTIC-SLT, Mohamed Abdou