Recognition error measurements from parameterized distance distributions
暂无分享,去创建一个
Formulations are obtained to estimate or predict the performance of a recognition system from parametric descriptions of the statistical distributions of distance measurements output by the recognizer. The dependence of performance estimates on the statistical parameters is shown, and, through this dependence, how performance in one decision mode, verification, is related to performance in another mode, identification. The validity of the formulations and their predictive capability are examined by means of a large experimental data base of distance samples obtained from a template based speaker recognition system. Error rates are tabulated directly from the distances and compared with performance predictions calculated from the formulas. It is shown that verification performance estimates agree well with direct error rate tabulations, while identification performance estimates are subject to a bias attributable to assumptions made in deriving the formulas. The extent to which the outcome of an identification experiment can be used to predict the outcome of a verification experiment, and vice-versa, is discussed.
[1] K. L. Shipley,et al. Evaluation of an isolated word recognizer in talker-dependent and talker-independent modes using a large telephone-band data base , 1984, ICASSP.
[2] L. Rabiner,et al. Isolated and Connected Word Recognition - Theory and Selected Applications , 1981, IEEE Transactions on Communications.
[3] F. Itakura,et al. Minimum prediction residual principle applied to speech recognition , 1975 .