[hts-users:00672] Speaker Adaptation

["Tamer Fares" <tamerfares@xxxxxxxxxxx>]

Hi Heiga

 

in order to make speaker adaptation using the HTS 2.0

I learned the htk tutorial and i conclude that to make a speaker adaptation i should do the following :

 

1.prepare the utterances for the adaptation

2.using the HHEd to build a regression class trees

3.perform static adaptation using the HERest to perform global adaptation then use this global adaptation as an input transformation to transform the model set

 

4.how can i use then the HMGens to generate the new parameters to be synthesis ?

 

Thanks

 

 

Tamer Fares

 

 

 

 

 

 

 

 

 

 

---

Express yourself instantly with MSN Messenger! MSN Messenger Download today it's FREE!