Dynamic Bayesian Multinets

TL;DR

This paper introduces dynamic Bayesian multinets that adapt their structure based on Markov chain states to improve classification, demonstrating superior performance in speech recognition tasks compared to traditional models.

Contribution

It presents a novel structure learning heuristic for dynamic Bayesian multinets that enhances classification accuracy by inducing sparse, discriminative, and class-conditional networks.

Findings

Outperform HMMs in speech recognition accuracy.

Use information-theoretic criteria for structure induction.

Achieve better results with fewer parameters.

Abstract

In this work, dynamic Bayesian multinets are introduced where a Markov chain state at time t determines conditional independence patterns between random variables lying within a local time window surrounding t. It is shown how information-theoretic criterion functions can be used to induce sparse, discriminative, and class-conditional network structures that yield an optimal approximation to the class posterior probability, and therefore are useful for the classification task. Using a new structure learning heuristic, the resulting models are tested on a medium-vocabulary isolated-word speech recognition task. It is demonstrated that these discriminatively structured dynamic Bayesian multinets, when trained in a maximum likelihood setting using EM, can outperform both HMMs and other dynamic Bayesian networks with a similar number of parameters.