HMMs are used because they have proved effective in a number of domains. The most significant of these is speech recognition, where it forms the basis of most commercial systems. They have also proved effective for a number of other tasks, such as handwriting recognition [PC97] and sign language recognition [SP95].
One of the most important advantages of HMMs is that they can easily be extended to deal with strong TC tasks. In the training stages, HMMs are dynamically assembled according to the class sequence. For example, if the class sequence was my hat, then two models for each word would be linked, with the last state of the first linking to the first state of the second. The re-estimation algorithm is then applied as usual. Once training on that instance is complete, the models are unlinked again. When recognition is attempted, large HMMs are assembled from the smaller individual models. This is done by converting from a grammar into a graph representation, then replacing each node in the graph with the appropriate model. This process is called ``embedded re-estimation''. To find out what the class sequence was, the most probable path is calculated. The path traversed corresponds to a sequence of classes, which is our final classification.
Because each HMM uses only positive data, they scale well; since new words can be added without affecting learnt HMMs. It is also possible to set up HMMs in such a way that they can learn incrementally. As mentioned above, grammar and other constructs can be built into the system by using embedded re-estimation. This gives the opportunity for the inclusion of high-level domain knowledge, which is important for tasks like speech recognition where a great deal of domain knowledge is available.
The basic theory of HMMs is also very elegant and easy to understand. This makes it easier to analyse and develop implementations for.