11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Shrinkage Model Adaptation in Automatic Speech Recognition

Jinyu Li (1), Yu Tsao (2), Chin-Hui Lee (3)

(1) Microsoft, USA
(2) NICT, Japan
(3) Georgia Institute of Technology, USA

We propose a parameter shrinkage adaptation framework to estimate models with only a limited set of adaptation data to improve accuracy for automatic speech recognition, by regularizing an objective function with a sum of parameter-wise power q constraint. For the first attempt, we formulate ridge maximum likelihood linear regression (MLLR) and ridge constraint MLLR (CMLLR) with an element-wise square sum constraint to regularize the objective functions of the conventional MLLR and CMLLR, respectively. Tested on the 5k-WSJ0 task, the proposed ridge MLLR and ridge CMLLR algorithms give significant word error rate reduction from the errors obtained with standard MLLR and CMLLR in an utterance-by-utterance unsupervised adaptation scenario.

Full Paper

Bibliographic reference.  Li, Jinyu / Tsao, Yu / Lee, Chin-Hui (2010): "Shrinkage model adaptation in automatic speech recognition", In INTERSPEECH-2010, 1656-1659.