Probability estimation by feed-forward networks in continuous speech recognition

Abstract
We review the use of feed-forward networks as estimators of probabilitydensities in hidden Markov modelling. In this paper we are mostlyconcerned with radial basis functions (RBF) networks. We note the isomorphismof RBF networks to tied mixture density estimators; additionally wenote that RBF networks are trained to estimate posteriors rather than thelikelihoods estimated by tied mixture density estimators. We show how theneural network training should be modified to resolve this...

This publication has 11 references indexed in Scilit: