Minimum classification error training of hidden Markov models for handwriting recognition

This paper evaluates the application of the Minimum Classification Error (MCE) training to online-handwritten text recognition based on Hidden Markov Models. We describe an allograph-based, character level MCE training aimed at minimizing the character error rate while enabling flexibility in writing style. Experiments on a writer-independent discrete character recognition task covering all alpha-numerical characters and keyboard symbols show that MCE achieves more than 30% character error rate reduction compared to the baseline Maximum Likelihood-based system.