Large Margin Training for Hidden Markov Models with Partially Observed States

Trinh Minh Tri Do (1) , Thierry Artières (1)

1 MALIRE - Machine Learning and Information Retrieval

Large margin learning of Continuous Density HMMs with a partially labeled dataset has been extensively studied in the speech and handwriting recognition fields. Yet due to the non-convexity of the optimization problem, previous works usually rely on severe approximations so that it is still an open problem. We propose a new learning algorithm that relies on non-convex optimization and bundle methods and allows tackling the original optimization problem as is. It is proved to converge to a solution with accuracy ε with a rate O (1/ε). We provide experimental results gained on speech and handwriting recognition that demonstrate the potential of the method.

Domaines: Informatique [cs]

Trinh Minh Tri Do, Thierry Artières. Large Margin Training for Hidden Markov Models with Partially Observed States. International Conference on Machine Learning (ICML), Jun 2009, Montreal, Canada. pp.265-272, ⟨10.1145/1553374.1553408⟩. ⟨hal-01294610⟩