Hi :
When I use the tool
HVite to calculate the score of the fulllab of a sentence and the model used is
the clusterd context dependent model , why the scores I get are all above 0
which is very different from the log likelyhood score in the speech recongnition
(always a minus number) ? Is there anything wrong ? I use the 12 order mfcc
parameter and the mmf contains both the spactra model and the f0 model.
thank you.
|