ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Local projections and support vector based feature selection in speech recognition

Antonio Miguel, Alfonso Ortega, L. Buera, Eduardo Lleida

In this paper we study a method to provide noise robustness in mismatch conditions for speech recognition using local frequency projections and feature selection. Local time-frequency filtering patterns have been used previously to provide noise robust features and a simpler feature set to apply reliability weighting techniques. The proposed method combines two techniques to select the feature set, first a reliability metric based on information theory and, second, a support vector set to reduce the errors. The support vector set provides the most representative examples which have influence in the error rate in mismatch conditions, so that only the features which incorporate implicit robustness to mismatch are selected. Some experimental results are obtained with this method compared to baseline systems using the Aurora 2 database.


doi: 10.21437/Interspeech.2009-10

Cite as: Miguel, A., Ortega, A., Buera, L., Lleida, E. (2009) Local projections and support vector based feature selection in speech recognition. Proc. Interspeech 2009, 48-51, doi: 10.21437/Interspeech.2009-10

@inproceedings{miguel09_interspeech,
  author={Antonio Miguel and Alfonso Ortega and L. Buera and Eduardo Lleida},
  title={{Local projections and support vector based feature selection in speech recognition}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={48--51},
  doi={10.21437/Interspeech.2009-10}
}