Maximum mutual information training of hidden Markov models with vector linear predictors.
K. K. ChinPhilip C. WoodlandPublished in: INTERSPEECH (2002)
Keyphrases
- hidden markov models
- mutual information
- linear predictors
- discriminative training
- baum welch
- image registration
- speech recognition
- markov models
- conditional random fields
- similarity measure
- sequential data
- feature selection
- hidden states
- appearance model
- training set
- feature vectors
- minimum classification error
- prediction error
- wavelet transform