Normalization and Adaptation by Consistently Employing Map Estimation

Abstract

The purpose of this paper is to develop a feature and model space adaptation method that improves speech recognition performance regardless of the amount of adaptation data. We propose a maximum a posteriori (MAP)-based Bayesian estimation approach that is consistently applied to normalization of feature spaces and adaptation of model parameters (i.e… (More)

5 Figures and Tables

Topics

  • Presentations referencing similar topics