23 May 2013 Significance test with data dependency in speaker recognition evaluation
Author Affiliations +
Abstract
To evaluate the performance of speaker recognition systems, a detection cost function defined as a weighted sum of the probabilities of type I and type II errors is employed. The speaker datasets may have data dependency due to multiple uses of the same subjects. Using the standard errors of the detection cost function computed by means of the two-layer nonparametric two-sample bootstrap method, a significance test is performed to determine whether the difference between the measured performance levels of two speaker recognition algorithms is statistically significant. While conducting the significance test, the correlation coefficient between two systems’ detection cost functions is taken into account. Examples are provided.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jin Chu Wu, Alvin F. Martin, Craig S. Greenberg, Raghu N. Kacker, Vincent M. Stanford, "Significance test with data dependency in speaker recognition evaluation", Proc. SPIE 8734, Active and Passive Signatures IV, 87340I (23 May 2013); doi: 10.1117/12.2014536; https://doi.org/10.1117/12.2014536
PROCEEDINGS
13 PAGES


SHARE
Back to Top