Linear feature space projections for speaker adaptation

Abstract

We extend the well-known technique of constrained Maximum Likelihood Linear Regression (MLLR) to compute a projection (instead of a full rank transformation) on the feature vectors of the adaptation data. We model the projected features with phone-dependent Gaussian distributions and also model the complement of the projected space with a single class… (More)
DOI: 10.1109/ICASSP.2001.940833

1 Figure or Table

Topics

  • Presentations referencing similar topics