Refinement of a Structured Language Model

A new language model for speech recognition inspired by linguistic analysis develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history in an attempt to complement the locality of currently used n-gram Markov models.

Abstract

A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history — thus enabling the use of extended distance dependencies — in an attempt to complement the locality of currently used n-gram Markov models. The model, its probabilistic parametrization, a reestimation algorithm for the model parameters and a set of experiments meant to evaluate its potential for speech recognition are presented.