Feature adaptation based on Baussian 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 [1] 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. © 2006 IEEE.