STiLL - Speech Technology in Language Learning
May 25-27, 1998
A theoretical framework, with much research support, is presented as a basis for the use of technology in language learning. According to the FLMP, well-learned patterns are recognized in accordance with a general algorithm, regardless of the modality or particular nature of the patterns. Multiple continuously-valued sources of information are evaluated, integrated, and matched against prototype descriptions in memory, and an identification decision is made on the basis of the relative goodness of match of the stimulus information with the relevant prototype descriptions. Three important properties are 1) the sources are optimally combined, 2) the sources are complementary, and 3) visible speech is a robust contribution to speech perception. The technology developed in our research can be leveraged within our theoretical framework to provide a novel and potentially productive pedagogy for language learning.
Bibliographic reference. Massaro, Dominic W. / Cohen, Michael M. (1998): "Visible speech and its potential value for speech training for hearing-impaired perceivers", In STiLL-1998, 171-174.