[hts-users:01762] HInit: Too Few Observation Sequences [0]

[Esther Klabbers <klabbers@xxxxxxxxxxxx>]

I'm trying to create a new voice using HTS 2.1. I've been able to run  
tests on existing voices and that has worked well. I've set up my data  
the way I think it needs to be set up. However, when I run "make  
voice" I get an error. It says it doesn't have any instances of the  
first phone "aa". My label files contain 942 instances of this phoneme  
and they're all longer than 5 ms. The label format is converted to HTK  
format. What could I be doing wrong?

Here is the error:

/usr/local/HTS-2.1/bin/HInit -A -C /Users/klabbers/Projects/HTS- 
demo_OGI-AS/configs/t
rn.cnf -D -T 1 -S /Users/klabbers/Projects/HTS-demo_OGI-AS/data/scp/ 
train.scp -m 1 -u
 tmvw -w 3 -H /Users/klabbers/Projects/HTS-demo_OGI-AS/models/qst001/ 
ver1/cmp/init.mm
f -M /Users/klabbers/Projects/HTS-demo_OGI-AS/models/qst001/ver1/cmp/ 
HInit -I /Users/
klabbers/Projects/HTS-demo_OGI-AS/data/labels/mono.mlf -l aa -o aa / 
Users/klabbers/Pr
ojects/HTS-demo_OGI-AS/proto/ver1/state-5_stream-4_mgc-75_lf0-3.prt

HTK Configuration Parameters[9]
  Module/Tool     Parameter                  Value
#                 MINDUR                         5
#                 MAXSTDDEVCOEF                 10
#                 APPLYDURVARFLOOR              TRUE
#                 DURVARFLOORPERCENTILE          1.000000
#                 VFLOORSCALESTR  Vector 4 0.01 0.01 0.01 0.01
#                 MINLEAFOCC                     0
#                 NATURALWRITEORDER              TRUE
#                 NATURALREADORDER              TRUE
#                 APPLYVFLOOR                 TRUE

Initialising  HMM /Users/klabbers/Projects/HTS-demo_OGI-AS/proto/ver1/ 
state-5_stream-
4_mgc-75_lf0-3.prt . . .
 States   :   2  3  4  5  6 (width)
 Mixes  s1:   1  1  1  1  1 ( 75  )
 ( 75  )
 Num Using:   0  0  0  0  0
 Mixes  s2:   2  2  2  2  2 (  1  )
 ( MSD  <=  1 )
 Num Using:   0  0  0  0  0
 Mixes  s3:   2  2  2  2  2 (  1  )
 ( MSD  <=  1 )
 Num Using:   0  0  0  0  0
 Mixes  s4:   2  2  2  2  2 (  1  )
 ( MSD  <=  1 )
 Num Using:   0  0  0  0  0
 Parm Kind:  USER
 Number of owners = 1
 SegLab   :  aa
 maxIter  :  20
 epsilon  :  0.000100
 minSeg   :  1
 Updating :  Means Variances MixWeights/DProbs TransProbs

 - system is PLAIN
  ERROR [+2121]  HInit: Too Few Observation Sequences [0]
 FATAL ERROR - Terminating program /usr/local/HTS-2.1/bin/HInit
Error in /usr/local/HTS-2.1/bin/HInit  -A    -C /Users/klabbers/ 
Projects/HTS-demo_OGI
-AS/configs/trn.cnf -D -T 1 -S /Users/klabbers/Projects/HTS-demo_OGI- 
AS/data/scp/trai
n.scp                -m 1 -u tmvw    -w 3 -H /Users/klabbers/Projects/ 
HTS-demo_OGI-AS
/models/qst001/ver1/cmp/init.mmf -M /Users/klabbers/Projects/HTS- 
demo_OGI-AS/models/q
st001/ver1/cmp/HInit -I /Users/klabbers/Projects/HTS-demo_OGI-AS/data/ 
labels/mono.mlf
 -l aa -o aa /Users/klabbers/Projects/HTS-demo_OGI-AS/proto/ver1/ 
state-5_stream-4_mgc
-75_lf0-3.prt


Esther Klabbers
Assistant Professor,
Center for Spoken Language Understanding (CSLU),
Division of Biomedical Computer Science (BMCS)
Oregon Health & Science University (OHSU)

20000 NW Walker Road / Beaverton, OR 97006
Office: +1-503-748-3005 / Fax: +1-503-748-1306
http://www.cslu.ogi.edu/people/klabbers