We present a Bayesian analysis of the evaluation of speaker detection performance. We use expectation of utility to confirm that likelihood-ratio is both an optimum and application-independent form of output for speaker detection systems. We point out that the problem of likelihood-ratio calculation is equivalent to the problem of optimization of decision thresholds. It is shown that the decision cost that is used in the existing NIST evaluations effectively forms a utility (a proper scoring rule) for the evaluation of the quality of likelihood-ratio presentation. As an alternative, a logarithmic utility (a strictly proper scoring rule) is proposed. Finally, an information-theoretic interpretation of the expected logarithmic utility is given. It is hoped that this analysis and the proposed evaluation method will promote the use of likelihood-ratio detector output rather than decision output.
Cite as: Brümmer, N. (2004) Application-independent evaluation of speaker detection. Proc. The Speaker and Language Recognition Workshop (Odyssey 2004), 33-40
@inproceedings{brummer04_odyssey,
author={Niko Brümmer},
title={{Application-independent evaluation of speaker detection}},
year=2004,
booktitle={Proc. The Speaker and Language Recognition Workshop (Odyssey 2004)},
pages={33--40}
}