Advances in automatic speech recognition by imitating spreading activation

Abstract

Inspired by recent insights into the properties of statistical word cooccurrences, we propose a mechanism which imitates spreading activation in the human mind in order to improve the identification of words during the automatic speech recognition process. This mechanism is able to make accurate semantic predictions about the currently uttered word as well as about words which are likely to come in the rest of a sentence. A robust automatic disambiguation algorithm provides a framework for semantic clustering, which allows to avoid the inherent polysemy problem.