Joint training of non-negative Tucker decomposition and discrete density hidden Markov models.
Meng SunHugo Van hammePublished in: Comput. Speech Lang. (2013)
Keyphrases
- hidden markov models
- baum welch
- discriminative training
- speech recognition
- viterbi algorithm
- discriminative classifiers
- conditional random fields
- markov models
- hidden state
- sequence classification
- tensor factorization
- gesture recognition
- handwritten word recognition
- sequential data
- training set
- hidden states
- minimum classification error
- automatic speech recognition
- em algorithm
- maximum likelihood
- keyword spotting
- acoustic models
- hierarchical hidden markov model