Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Speaker Clustered Regression-Class Trees for MLLR Adaptation

Arindam Mandal (1), Mari Ostendorf (1), Andreas Stolcke (2)

(1) University of Washington, USA; (2) SRI International, USA

A speaker clustering algorithm is presented that is based on an eigenspace representation of Maximum Likelihood Linear Regression (MLLR) transformations and is used for training cluster-dependent regression-class trees for MLLR adaptation. It is shown that significant automatic speech recognition (ASR) system performance gains are possible by choosing the best regression-class tree structure for individual speakers. To take advantage of the potential gains, an algorithm for combining the MLLR mean transformations from cluster-specific trees is described that effectively results in a soft regression-class tree. In conversational speech recognition, only small overall improvements are obtained, but the number of speakers that have performance degradation due to adaptation is reduced by over 70%.

Full Paper

Bibliographic reference.  Mandal, Arindam / Ostendorf, Mari / Stolcke, Andreas (2006): "Speaker clustered regression-class trees for MLLR adaptation", In INTERSPEECH-2006, paper 1763-Tue2BuP.11.