A phonologically motivated input representation for the modelling of auditory word perception in continuous speech

Representational choices are crucial to the success of connectionist modelling. Most previous models of auditory word perception in continuous speech have relied upon a traditional Chomsky-Halle style inventory of features; many have also postulated a localist phonemic level of representation mediating a featural and a lexical level. A different immediate representation of the speech input is proposed, motivated by current developments in phonological theory, namely Government Phonology. The proposed input representation consists of nine elements with physical correlates. A model of speech perception employing this input representation is described. Successive bundles of elements arrive across time at the input. Each is mapped, by means of recurrent connections, onto a window representing the current bundle and a context consisting of three such bundles either side of the current bundle. Simulations demonstrate the viability of the proposed input representation. A simulation of the compensation for co-articulation effect demonstrates an interpretation which does not involve top-down interaction between lexical and lower levels. The model described as envisaged as part of a wider model of language processing incorporating semantic and orthographic levels of representation, with no local lexical entries.