Topic-based language models using EM
Published • Sep 5, 1999
NobleIDNI4P11W21R54S10
Authors:,
Daniel Gildea
Thomas Hofmann
Abstract
The performance of global affine and nonlinear transformations for speaker adaptation in a hidden Markov model (HMM) speech recognition system are compared in this paper. The nonlinear transformation was obtained with a multilayer perceptron network (MLP) which was trained during the adaptation proc...
Finding related papers...
Discussions
(0)No comments yet
Be the first to share your thoughts!