Speaker adaptive training using shift-MLLR

In this paper a novel method for speaker adaptive training (SAT), based on Gaussian mean offset adaptation, so called Shift-MLLR, is presented. The method differs from previous SAT methods, where linear transformations of Gaussian means or features are utilized, in that only an offset vector is used for adaptation, but instead the number of regression classes is increased. This is shown to allow an efficient implementation. Furthermore, the use of word posterior confidence measures for Shift-MLLR is investigated, also in combination with the proposed SAT method. The presented methods are integrated into a state of the art speech recognition system, and performance is contrasted with Shift-MLLR without SAT, as well as with MLLR. Large and consistent improvements in word error rate are observed from the new SAT method, as well as from confidence based Shift-MLLR. The combination of the new speaker adaptive training method with confidence based estimation show consistent improvements.