Statistical Language Models for Online Handwritten Sentence Recognition

This paper investigates the integration of a statistical language model into an on-line recognition system in or-der to improve word recognition in the context of handwrit-ten sentences. Two kinds of models have been considered: n-gram and n-class models (with a statistical approach to create word classes). All these models are trained over the Susanne corpus and experiments are carried out on sen-tences from this corpus which were written by several writ-ers. The use of a statistical language model is shown to im-prove the word recognition rate and the relative impact of the different language models is compared. Furthermore, we illustrate the interest to dejine an optimal cooperation between the language model and the recognition system to re-enforce the accuracy of the system. 1