[hts-users:02635] Re: discrete hmm model training

["Heiga ZEN (Byung Ha CHUN)" <heiga.zen@xxxxxxxxxxxxxxxxx>]

Hi,

Gergely Bakos wrote (2010/12/01 1:47):

> I would like to use HTS 2.1.1. for discrete HMM model training, but with the HTK
> version 3.4.1 + HTS 2.1.1. patch it doesn't work. I think, the problem is with
> the HTS patch, I've doublechecked the HMM definition file, and the training
> files, and they are correct. (I've tried training discrete HMMs without the
> patch, with HTK 3.4.1, and it worked.)
>
> Is there any way, or option, to solve the problem?

HTS has not been fully tested with discrete HMM model due to time constraints. 
If you can figure out the problems and report them to this ML, someone will 
spare his/her time to fix the problems.  For now, the easiest solution is to use 
HTK rather than HTS.

Regards,

Heiga ZEN (Byung Ha CHUN)

======================================================================
NOTE: The information in this email and any attachments may be confidential
and/or legally privileged. This message may be read, copied and used only by
the intended recipient. If you are not the intended recipient, please
destroy this message, delete any copies held on your system and notify the
sender immediately.

Toshiba Research Europe Limited, registered in England and Wales (2519556).
Registered Office: 208 Cambridge Science Park, Milton Road, Cambridge
CB4 0GZ, England. Web: http://www.toshiba-europe.com/research/crl
======================================================================

______________________________________________________________________
This email has been scanned by the MessageLabs Email Security System.
For more information please visit http://www.messagelabs.com/email 
______________________________________________________________________