Premium
A Connectionist Model of Phonological Representation in Speech Perception
Author(s) -
Gaskell M. Gareth,
Hare Mary,
MarslenWilson William D.
Publication year - 1995
Publication title -
cognitive science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.498
H-Index - 114
eISSN - 1551-6709
pISSN - 0364-0213
DOI - 10.1207/s15516709cog1904_1
Subject(s) - connectionism , computer science , perception , inference , speech perception , natural language processing , speech recognition , variation (astronomy) , artificial intelligence , abstraction , psychology , artificial neural network , philosophy , physics , epistemology , neuroscience , astrophysics
A number of recent studies have examined the effects of phonological variation on the perception of speech. These studies show that both the lexical representations of words and the mechanisms of lexical access are organized so that natural, systematic variation is tolerated by the perceptual system, while a general intolerance of random deviation is maintained. Lexical abstraction distinguishes between phonetic features that form the invariant core of a word and those that are susceptible to variation. Phonological inference relies on the context of surface changes to retrieve the underlying phonological form. In this article we present a model of these processes in speech perception, based on connectionist learning techniques. A simple recurrent network was trained on the mapping from the variant surface form of speech to the underlying form. Once trained, the network exhibited features of both abstraction and inference in its processing of normal speech, and predicted that similar behavior will be found in the perception of nonsense words. This prediction was confirmed in subsequent research (Gaskell & Marslen‐Wilson, 1994).