Comparing and evaluating HMM ensemble training algorithms using train and test and condition number criteria

Richard I. A. Davis, Brian C. Lovell

Abstract: Hidden Markov Models have many applications in signal processing and pattern recognition, but their convergence-based training algorithms are known to suffer from over-sensitivity to the initial random model choice. This paper describes the boundary between regions in which ensemble learning is superior to Rabiner’s multiple-sequence Baum-Welch training method, and proposes techniques for determining the best method in any arbitrary situation. It also studies the suitability of the training methods using the condition number, a recently proposed diagnostic tool for testing the quality of the model. A new method for training Hidden Markov Models called the Viterbi Path Counting algorithm is introduced and is found to produce significantly better performance than current methods in a range of trials.