Boosting HMMs with an application to speech recognitionReport as inadecuate

Boosting HMMs with an application to speech recognition - Download this document for free, or read online. Document in PDF available to download.

IDIAP, 2003

Boosting is a general method for training an ensemble of classifiers with a view to improving performance relative to that of a single classifier. While the original AdaBoost algorithm has been defined for classification tasks, the current work examines its applicability to sequence learning problems. In particular, different methods for training HMMs on sequences and for combining their output are investigated in the context of automatic speech recognition.

Keywords: learning Note: Accepted for publication in ICASSP 2004 Reference EPFL-REPORT-82952

Author: Dimitrakakis, Christos; Bengio, Samy



Related documents