Re:Single Speaker Speech Recognition with Hidden Markov Models
by kastnerkyle on Friday May 23, 2014 @04:44AM
(#7788507)
Interesting - I've never tried Viterbi training. Maybe it is worth implementing after all. I plan to do a hybrid DNN-HMM (or whatever it is called now) with pylearn2 in a followup post.
[ Parent
| on HN ]
There are no comments on this comment yet.