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

[hts-users:01926] Re: Welcome to our (hts-users ML) You are added automatically


Hi

wangxiang68@xxxxxxxxx wrote (2009/03/18 8:30):

I'm a HTS-2.1 user, encounter problems while adapting the spk1 model to sp2 model by MLLR.
>
   1, what is the meaning of xForms?

Linear transforms such as MLLRMEAN, MLLRCOV, and CMLLR transforms.

2, Is the basic configuration of HTS-2.1 for speaker adaptation like this? Using HERest to estimate the MLLR transformations to store in the xforms files, and using HMGens to do the model transformation; Am I right ?

You're right.

Regards,

Heiga ZEN (Byung Ha CHUN)

--
Heiga ZEN (Byung Ha CHUN)
Speech Technology Group
Cambridge Research Lab
Toshiba Research Europe
phone: +44 1223 436975

______________________________________________________________________
This email has been scanned by the MessageLabs Email Security System.
For more information please visit http://www.messagelabs.com/email ______________________________________________________________________
Follow-Ups
[hts-users:01928] Re: Welcome to our (hts-users ML) You are added automatically, 王翔
References
[hts-users:01915] Re: Welcome to our (hts-users ML) You are added automatically, 王翔