Dear Keiichiro Oura:
I have read your paper named "A fully consisten hidden semi-markov
model-based speech recognition system". I want to ask you some questiones
aboust hsmm and HTS.
The first question is that the tool HFst in HTS 2.1.1 beta version can
convert MSD-HSMM to FST?
The second question is HVite in HTS2.1 can support MSD-HSMM decode?
The last question is that how to use WFST to decode speech as your paper described?
Thanks a lot! 2010-04-17
Chongjia Ni
|