An introduction to hidden Markov models and Bayesian networks

We provide a tutorial on learning and inference in hidden Markov models in the context of the recent literature on Bayesian networks. This perspective makes it possible to consider novel generalizations of hidden Markov model s with multiple hidden state variables, multiscale representations, and mix ed discrete and continuous variables. Although exact inference in these gen eralizations is usually intractable, one can use approximate inference algo rithms such as Markov chain sampling and variational methods. We describe h ow such methods are applied to these generalized hidden Markov models. We c onclude this review with a discussion of Bayesian methods for model selecti on in generalized HMMs.