Title: MLLR Adaptation Techniques for Pronunciation Modeling

Authors: Bill Byrne, Veera Venkataramani

Abstract: Multiple regression class MLLR transforms are investigated for use with pronunciation models that predict variation in the observed pronunciations given the phonetic context. Regression classes can be constructed so that MLLR transforms can be estimated and used to model specific acoustic changes associated with pronunciation variation. The effectiveness of this modeling approach is evaluated on the phonetically transcribed portion of the SWITCHBOARD conversational speech corpus.

a01bb036.ps a01bb036.pdf