A Combined MAP + MLLR Approach for Speaker Adaptation

A new approach for speaker adaptation consisting of MLLR adaptation enriched by a special weighting scheme followed by MAP adaptation is presented. While the standard MLLR approach increases the error rate for the considered small amounts of adaptation data in on-line, unsupervised adaptation, our approach can reduce the error by up to 30%. This result can further be improved by switching to MAP adaptation, yielding a final reduction in error rate of 38.6% compared to the speaker independent (SI) system.