9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

A Minimum Classification Error Based Distance Measure for Template Based Speech Recognition

Mike Matton, Dirk Van Compernolle, Ronald Cools

Katholieke Universiteit Leuven, Belgium

In this paper we investigate the minimum classification error (MCE) criterion for the training of distance measures for template based speech recognition. These MCE-based distance measures are illustrated with example experiments on the Wall Street Journal 5k benchmark for continuous speech recognition.

Full Paper

Bibliographic reference.  Matton, Mike / Compernolle, Dirk Van / Cools, Ronald (2008): "A minimum classification error based distance measure for template based speech recognition", In INTERSPEECH-2008, 2386-2389.