Fast Speaker Adaptation of Large Vocabulary Continuous Density Speech Recognizer Using a Density Combination Approach

Maximum Likelihood transformationadaptation techniques have proven successful, but it is believed that faster convergence to speaker dependent (SD) performance can be achieved if we incorporate some form of a-priori knowledge in the adaptation process. In this paper, instead of estimating one linear transform per class of models for each new speaker, we transform the speaker-independent (SI) models using multiple linear transforms and a weight vector. To reduce the number of adaptation parameters, the multiple linear transforms are generated from training speakers and the adaptation parameters consist of a single weight vector per class. This can be seen as incorporating a-priori knowledge to our estimation process. Experiments conducted on the Spoken Language Translator database in the Swedish Language using SRI’s DECIPHER system, show that the new method outperforms MLLR on very limited adaptation data.