You are here:Home Courses Archived courses Speech Processing (up to 2016-17) Automatic speech recognition Hidden Markov Models The model

The model

Once we have an initial conceptual understanding of generative modelling, we can develop this simple generative model of variable-duration sequences.

  • The Bayesian view

    This is a way of understanding probability that will be most useful for understanding HMMs.

  • A generative model of sequences

    How to generate a sequence of observations from our model.

  • Duration

    Now we have a sequence of observations, we need to model its duration.

  • The complete model

    Finally we put all those pieces together and we have the complete HMM model, which is actually rather simple.

Reading

Holmes & Holmes – Chapter 9 – Stochastic Modelling

May be helpful as a complement to the essential readings.