Second Workshop on Child, Computer and Interaction (WOCCI 2009)
Cambridge, MA, USA
In this article we present a novel approach to reference
verification, the problem of determining if a speakers' utterance
matches a specificied reference (text) string, and discuss its
application to a reading tracker system for children's speech.
Unlike other reading tracker systems proposed in the literature that are built over conventional speech recognizers with ad-hoc language models, the reading tracker described here is designed specifically for the task of estimating whether a child has read an expected sequence of words out loud; the tracker is designed to deal in a natural and flexible way with disfluencies that frequently appear in children's speech while reading out loud, (e.g., partial-words, repetitions, self-corrections, etc), and to overcome problems caused by using language models within the reference verification task. Two mechanisms have been introduced for this purpose, the utilization of filler models and the inclusion of backward inter-word transitions in the decoding network.
While this article focuses on the approach used to overcome errors observed in previous systems, the performance of this system will be evaluated on a corpus of children's speech while reading out loud and compared to the performance of a "traditional" reading tracker system that are built on top of a speech recognition system. The results of this comparison will be presented at WOCCI 2009.
Bibliographic reference. Bolaños, Daniel / Ward, Wayne H. / Cole, Ronald A. (2009): "A reference verification framework and its application to a childrens speech reading tracker", In WOCCI-2009, 105-106.