Combination of explicit segmentation with Seq2Seq recognition for fine analysis of children handwriting

We consider the task of analyzing children handwriting in context a dictation task. The objective is to detect orthographic and phonological errors. To achieve this goal, we extend an existing analysis engine, based on explicit segmentation handwritten input, originally developed for copying exercises. present new approach, combination engine with deep learning word recognition approach order improve both performance. Explicit needs prior knowledge, network predictions are reliable approximation ground truth which can guide process. propose combine multiple knowledge strategies further Furthermore, exploit approximate implicit optimize process terms complexity.