Construction of language models for an handwritten mail reading system

Olivier Morillot, Laurence Likforman-Sulem, Emmanuèle Grosicki, Christian Viard-Gaudin, Richard Zanibbi
2012 Document Recognition and Retrieval XIX  
This paper presents a system for the recognition of unconstrained handwritten mails. The main part of this system is an HMM recognizer which uses trigraphs to model contextual information. This recognition system does not require any segmentation into words or characters and directly works at line level. To take into account linguistic information and enhance performance, a language model is introduced. This language model is based on bigrams and built from training document transcriptions
more » ... Different experiments with various vocabulary sizes and language models have been conducted. Word Error Rate and Perplexity values are compared to show the interest of specific language models, fit to handwritten mail recognition task.
doi:10.1117/12.911965 dblp:conf/drr/MorillotLG12 fatcat:ug66hd42zjbanidwyc4fuvgsui