Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Feature Adaptation Using Projection of Gaussian Posteriors

Karthik Visweswariah, Peder Olsen

IBM T.J. Watson Research Center, Yorktown Heights, NY, USA

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 adapt the original features. Parameters are estimated to maximize the likelihood of the test data. The modeling framework used is based on the fMPE models [1]. We observe significant gains (17% relative) on a test data base recorded in a car. We also see significant gains on top of FMLLR (38% relative over the baseline and 8.5% relative over FMLLR).

Full Paper

Bibliographic reference.  Visweswariah, Karthik / Olsen, Peder (2005): "Feature adaptation using projection of Gaussian posteriors", In INTERSPEECH-2005, 1785-1788.