Re:Single Speaker Speech Recognition with Hidden Markov Models
by iori42 on Friday May 23, 2014 @04:04AM
(#7788409)
In my experience Viterbi training alone is often enough to get reasonable accuracy, at least in speech recognition.
Instead of doing the more costly Baum-Welch training you can spend your time better elsewhere, e.g. use deep neural networks instead of GMMs or collect more data.
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.
- Divide all examples (observation sequences) uniformly into as many segments as the number of states.
- Cluster the observations corresponding to each state, and estimate the GMM using the cluster set so that each cluster corresponds to one multivariate Gaussian.
- Do this repeatedly until convergence: get the Viterbi alignment of all examples, use it to get new segments, and estimate the parameters again using the previous step.
Please correct me if I'm wrong. Also, I have two questions:
- What kind of accuracy increase should be expected if using both Viterbi training and Baum-Welch re-estimation, instead of just the latter?
- What kind of accuracy should be expected if only using Viterbi training?