ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

A minimum classification error based distance measure for template based speech recognition

Mike Matton, Dirk Van Compernolle, Ronald Cools

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.


doi: 10.21437/Interspeech.2008-125

Cite as: Matton, M., Compernolle, D.V., Cools, R. (2008) A minimum classification error based distance measure for template based speech recognition. Proc. Interspeech 2008, 2386-2389, doi: 10.21437/Interspeech.2008-125

@inproceedings{matton08_interspeech,
  author={Mike Matton and Dirk Van Compernolle and Ronald Cools},
  title={{A minimum classification error based distance measure for template based speech recognition}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={2386--2389},
  doi={10.21437/Interspeech.2008-125}
}