Learning hidden Markov models with persistent states by penalizing jumps.
Peter NystrupErik LindströmHenrik MadsenPublished in: Expert Syst. Appl. (2020)
Keyphrases
- hidden markov models
- sequence classification
- hidden state
- learning algorithm
- continuous hidden markov models
- sequential data
- prior knowledge
- markov models
- gesture recognition
- discriminative training
- state transition
- hierarchical structure
- viterbi algorithm
- conditional random fields
- speech recognition
- handwritten word recognition
- random effects
- maximum likelihood