7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

Improved Structural Maximum Likelihood Eigenspace Mapping for Rapid Speaker Adaptation

Bowen Zhou, John H. L. Hansen

University of Colorado at Boulder, USA

In this paper, we expand on a previously proposed algorithm entitled Structural Maximum Likelihood Eigenspace Mapping (SMLEM) [5, 6] for rapid speaker adaptation by exploring a variety of model clustering methods and incorporating a multi-stream approach. The SMLEM algorithm directly adapts speaker independent acoustic models to a test speaker by mapping the mixture Gaussian components from a speaker independent eigenspace to speaker dependent eigenspaces in a maximum likelihood manner, with very limited amounts of adaptation data. Evaluations are performed using the WSJ Spoke3 corpus. Employing the improved proposed methods, SMLEM consistently outperforms both standard MLLR and block diagonal MLLR for small amounts of adaptation data.

Full Paper

Bibliographic reference.  Zhou, Bowen / Hansen, John H. L. (2002): "Improved structural maximum likelihood eigenspace mapping for rapid speaker adaptation", In ICSLP-2002, 1433-1436.