[hts-users:00886] Re: Training by imposing decision trees
Simon King wrote (2007/10/27 15:11):
- use HHEd's "AU" command to synthesise *all* the models you need
(the ones you previously deleted from the MMF, plus any unseen ones)
One other small wrinkle - the HHEd manual says about the AU command:
"If the clustering was performed at the state level a prototype model
(an example of the same phone model occurring in a different context) is
found and a new HMM is constructed that shares the transition matrix
with the prototype model but consists of tied states selected using the
decision tree."
so (since HTS uses state clustering) you would have to have some models
loaded into HHEd in order to form these prototypes - I suppose you could
have just one such model per phone, in a bogus context, and then strip
out these models after you have synthesised the models you want
Simon
- References
-
- [hts-users:00876] Training by imposing decision trees, Thomas Drugman
- [hts-users:00877] Re: Training by imposing decision trees, Heiga ZEN (Byung Ha CHUN)
- [hts-users:00884] Re: Training by imposing decision trees, Simon King
- [hts-users:00885] Re: Training by imposing decision trees, Heiga ZEN (Byung Ha CHUN)