This paper describes a top-down word image generation model for holistic handwritten word recognition. To generate a word image, it uses likelihoods based, respectively, on a linguistic model, a segmentation model, and a character generation model. In the recognition process with respect to a given input image, it first generates, for each word in a dictionary of possible words, a word image th...

There is substantial neural evidence for the role of morphology (word-internal structure) in visual word recognition. We extend this work to auditory word recognition, drawing on recent evidence that phoneme prediction is central to this process. In a magnetoencephalography (MEG) study, we crossed morphological complexity (bruis-er vs. bourbon) with the predictability of the word ending (bourbo...

Continuous mapping models of spoken word recognition such as TRACE (McClelland and Elman, 1986) make robust predictions about a wide variety of phenomena. However, most of these models are interactive activation models with preset weights, and do not provide an account of learning. Simple recurrent networks (SRNs, e.g., Elman, 1990) are continuous mapping models that can process sequential patt...

We examined whether word recognition accuracy and latency of words children encounter during primary school across the upper grades can be predicted from form (word length, mean Levenshtein distance, frequency neighbors), meaning (free association network markers) exposure (corpus contextual diversity). As a measure recognition, 1454 (M = 10.1 years, SD 11.8 months, 52.4% girls) in grade 3, 4 5...