In M.A. Arbib (Ed.), The handbook of brain theory and neural networks (2^nd ed.). Cambridge, MA: MIT Press.

Connectionist models of speech processing.

Nick Chater, & Morten Christiansen

Introduction

Psycholinguistics refers to the empirical study of the human language processing system, typically using behavioral experiments. This chapter considers attempts to capture psycholinguistic data using connectionist models (Christiansen and Chater, 2001). We primarily focus on relatively ‘early’ aspects of speech processing--speech segmentation and word recognition.

This chapter has four sections. Connectionist Modeling: A Bridge Between Psycholinguistics and Brain Theory? outlines the gulf between theories of brain function and traditional account of language processing. Connectionist modeling promises to help span this gulf, by attempting to ground speech processing in a connectionist processing architecture, a type of architecture initially inspired by attempts to model the computational properties of the brain. The section Segmentation and Recognition: Two processes or one? asks how far the problem of segmenting speech into words occurs independently of word recognition—a critical question for computational modelling. Competition and Interaction in Word Recognition considers connectionist models of word recognition, and their interplay with empirical research and theory.

Click here to download a PDF version.

Home \| People \| Research \| Links \| Contact \| Publications \| Presentations

Please email suggestions/errors to mhc27@cornell.edu