Improvements in linear transform based speaker adaptation

Presents three forms of linear transform based speaker adaptation that can give better performance than standard maximum likelihood linear regression (MLLR) adaptation. For unsupervised adaptation, a lattice-based technique is introduced which is compared to MLLR using confidence scores. For supervised adaptation, estimation of the adaptation matrices using the maximum mutual information criterion is discussed which leads to the MMILR approach. Recognition experiments show that lattice MLLR can reduce word error rates on a Switchboard task by 1.4% absolute. For recognition of non-native speech from the Wall Street Journal database, a reduction in word error rate of 10-16% relative was obtained using MMILR compared to standard MLLR