Feature Adaptation Based on Gaussian Posteriors

In this paper we consider the use of non-linear methods for feature adaptation to reduce the mismatch between test and training conditions. The non-linearity is introduced by using the posteriors of a set of Gaussians to (softly) partition the observation space for feature adaptation. The modeling framework used is based on the fMPE models (D. Povey et al., 2005) applied to FMLLR matrices directly. However, the parameters are estimated to maximize the likelihood of the test data. We observe a relative gain of 14% on top of FMLLR, which was a 42% relative gain over the baseline