Discriminative Speaker Adaptation with Conditional Maximum Likelihood Linear Regression

Download: PDF.

“Discriminative Speaker Adaptation with Conditional Maximum Likelihood Linear Regression” by A. Gunawardana and W. Byrne. In Proc. of the European Conference on Speech Communication and Technology (EUROSPEECH), 2001.

Abstract

We present a simplified derivation of the extended Baum-Welch procedure, which shows that it can be used for Maximum Mutual Information (MMI) of a large class of continuous emission density hidden Markov models (HMMs). We use the extended Baum-Welch procedure for discriminative estimation of MLLR-type speaker adaptation transformations. The resulting adaptation procedure, termed Conditional Maximum Likelihood Linear Regression (CMLLR), is used successfully for supervised and unsupervised adaptation tasks on the Switchboard corpus, yielding an improvement over MLLR. The interaction of unsupervised CMLLR with segmental minimum Bayes risk lattice voting procedures is also explored, showing that the two procedures are complimentary.

Download: PDF.

BibTeX entry:

@inproceedings{gunawardana01:dllr_eurospeech01,
   author = {A. Gunawardana and W. Byrne},
   title = {Discriminative Speaker Adaptation with Conditional Maximum
	Likelihood Linear Regression},
   booktitle = {Proc. of the European Conference on Speech Communication
	and Technology (EUROSPEECH)},
   pages = {(4 pages)},
   year = {2001}
}

Back to Bill Byrne publications.