Affiliations: Centre for Language and Speech Technology, Radboud
University, P.O. Box 9103, 6500 HD Nijmegen, the Netherlands.
[email protected] | Centre for Language and Speech Technology, Radboud
University, Nijmegen, the Netherlands | ESAT, Katholieke Universiteit Leuven, Leuven,
Belgium | SPandH, Dept. of Computer Science, Sheffield
University, U.K.
Abstract: In this paper, we discuss a computational model that is able to
detect and build word-like representations on the basis of sensory input. The
model is designed and tested with a further aim to investigate how infants may
learn to communicate by means of spoken language. The computational model makes
use of a memory, a perception module, and the concept of 'learning
drive'. Learning takes place within a communicative loop between a
'caregiver' and the 'learner'.
Experiments carried out on three European languages with different
genetic background (Finnish, Swedish, and Dutch) show that a robust word
representation can be learned in using less than 100 acoustic tokens (examples)
of that word. The model is inspired by the memory structure that is assumed
functional for human cognitive processing.
Keywords: I5 pattern recognition, J5 arts and humanities, F5 theory of computation, miscellaneous (cognitive modelling)
