@InProceedings{Howard2011_26,
author = {Ian S. Howard and Piers Messum},
booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2011.},
title = {The computational architecture of Elija: a model of a young child that learns to pronounce},
year = {2011},
editor = {Bernd J. Kröger and Peter Birkholz},
month = mar,
pages = {138--145},
publisher = {TUDpress, Dresden},
abstract = {We describe the architecture and operation of Elija, a computational infant
that learns to pronounce speech sounds. Elija is modelled as an agent who can
interact with his environment but who has no a priori articulatory or perceptual
knowledge of speech. His sensory system responds to touch and acoustic input. He
judges the value of action and response using a reward mechanism, and can associate
and remember the correspondences between his actions, their reward, and prior and
subsequent sensory inputs. Elija first develops the ability to babble using
unsupervised learning, which is formulated as an optimization problem. Then he
takes advantage of tutored interactions with his caregivers. Such interactions consist
of naturalistic exchanges in which the caregivers reformulate Elija’s output. He uses
these to learn the importance of his productions and this process selects for good
productions and discards poor ones. In addition, using associative memory, the
reformulations build up a correspondence between his output and adult speech
sounds. This leads Elija to develop the ability to imitate words spoken by the
caregiver by parsing this input, with a DTW recognizer, in terms of previously heard
reformulations which he uses as its templates. He thereby identifies the sequence of
motor actions he can perform that his caregiver will take to be equivalent to each
word. In this way, Elija is able to learn the pronunciation of novel words.},
isbn = {978-3-942710-37-4},
issn = {0940-6832},
keywords = {Poster zu verschiedenen Themenbereichen},
url = {https://www.essv.de/pdf/2011_138_145.pdf},
}