Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Leveraging Speaker-Dependent Variation of Adaptation

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

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

This work introduces an automatic procedure for determining the size of regression class trees for individual speakers using an ensemble of speaker-level features to control the number of transformations, if any, that should be estimated by maximum likelihood linear regression. Experiments with a state-of-the-art speech recognition system that uses this procedure show improvements in word error rate for conversational telephone speech.

Full Paper

Bibliographic reference.  Mandal, Arindam / Ostendorf, Mari / Stolcke, Andreas (2005): "Leveraging speaker-dependent variation of adaptation", In INTERSPEECH-2005, 1793-1796.