A nonlinear unsupervised adaptation technique for speech recognition

Abstract

This paper describes a computationally inexpensive, nonlinear feature transformation technique for rapid adaptation of a speech recognition system to new acoustic conditions. One of the advantages of the method is that it does not require any initial decoding of the adaptation data for computing the nonlinear transform. This technique performs as well as the more expensive unsupervised MLLR technique. Furthermore, it significantly adds to the improvement when combined with unsupervised MLLR.