Recognising Embedded Words in Connected Speech: Context and Competition

in Proceedings of the Fourth Neural Computation and Psychology Workshop
J. A. Bullinaria, D. W. Glasspool, G. Houghton (Eds). London: Springer-Verlag
April 1997

Matt H. Davis, William D. Marslen-Wilson and M. Gareth Gaskell

E-mail: matt.davis@mrc-cbu.cam.ac.uk


Onset-embedded words (e.g. cap in captain) present a problem for accounts of spoken word recognition since information coming after the offset of the embedded word may be required for identification. We demonstrate that training a simple recurrent network to activate a representation of all the words in a sequence allows the network to learn to recognise onset-embedded words without requiring a training set that is already lexically segmented. We discuss the relationship between our model and other accounts of lexical segmentation and word recognition, and compare the model’s performance to psycholinguistic data on the recognition of onset-embedded words.