In the paper, we present a comparative study of several methods used nowadays in the field of feature and information extraction. We compared several Independent Component Analysis (ICA) algorithms together with the commonly used Principal Component Analysis (PCA) algorithm in two real-world tasks. The first task was a Voice Activity Detection (VAD), the second is Speaker Verification and Recognition (SVR). The VAD system as well as the SVR system benefited from the ICA decompositions. Moreover, a brief comparison of the information extraction ability is described.
Cite as: Trmal, J., Vanek, J., Müller, L., Zelinka, J. (2006) Independent components for acoustic modeling. Proc. Interspeech 2006, paper 1526-Thu2BuP.3, doi: 10.21437/Interspeech.2006-623
@inproceedings{trmal06_interspeech,
author={Jan Trmal and Jan Vanek and Ludek Müller and Jan Zelinka},
title={{Independent components for acoustic modeling}},
year=2006,
booktitle={Proc. Interspeech 2006},
pages={paper 1526-Thu2BuP.3},
doi={10.21437/Interspeech.2006-623}
}