HI All,

I've was able to create a custom acoustic model folling this tutorial: http://www.voxforge.org/home/dev/acousticmodels/linux

The recognition of my voice is great.  Next I wanted to use this data to adapt the Voxforge acoustic model to better recognize my voice.  Hpwever, i am running into the following error in Step 4 of Adapt with the following command:

HVite -A -D -T 1 -l '*' -o SWT -b SENT-END -C config -H macros -H hmmdefs -i adaptPhones.mlf -m -t 250.0 150.0 1000.0 -y lab -a -I adaptWords.mlf -S adapt.scp dict tiedlist

The error is:

Aligning File: ./mfcc/sample19.mfc
Created lattice with 6 nodes / 5 arcs from label file
  ERROR [+8231]  GetHCIModel: Cannot find hmm [t-]en[+???]
 FATAL ERROR - Terminating program ../../../../HTK_july24_2010/htk/HTKTools/HVite

Can anyone help me with what this means?  I don't have a clue and can't find any info online.

Thanks a lot,

Franci

--- (Edited on 7/25/2010 9:14 pm [GMT-0500] by Visitor) ---