sretools-package: Compute performance measures for Speaker Recognition...

In davidavdav/sretools.R: Compute error metrics and make DET plots for NIST-like Speaker Recognition Evaluations

Description

This can compute various performance measures for an automatic speaker recognition system. It knows target truth values about NIST SRE-2008 and EVALITA 2009 evaluations, and will read submission files and augment the data with target and aother meta information. The package can equalized for unbalanced conditions within an evaluation, and computes modern evaluation measures such as C_{llr}.

Details

Package:	sretools
Type:	Package
Version:	0.5
Date:	2011-10-31
License:	GPL-2
LazyLoad:	yes

The package provides tools for computing evaluation metrics on standard trial sets in speaker recognition. With read.sre a standard submission file can be read into an sre structure. Then, with det.sre the performance measures are computed and a structure is prepared for plotting. summary.det shows basic performance measures, and plot.det will make a DET plot. Additionaly, APE plots can be generated using ape.plot.

Author(s)

David A. van Leeuwen.

Maintainer: <[e-mail]>

References

Alvin Martin et al, “The DET Curve in Assessment of Detection Task Performance,” Proc. Interspeech, 1895–1898 (1997). Niko Br\"ummer and Johan du Preez, “Application-independent evaluation of speaker detection,” Computer, Speech and Language 20, 230–275, (2006). David van Leeuwen and Niko Br\"ummer, “An Introduction to Application-Independent Evaluation of Speaker Recognition System,” LNCS 4343 (2007). Foster Provost and Tom Fawcett, “Analysis and Visualization of Classifier Performance: Comparison under Imprecise Class and Cost Distributions,” Third International Conference on Knowledge Discovery and Data Mining (1997).

See Also

read.sre, det.sre, plot.det.

Examples

## RU submission to EVALITA speaker recognition applications track
data(ru.2009)
## inspect details of data frame
ru.2009[1,]
setDCF("evalita")
## look at TC6 train condition and TS2 test condition (easiest task:-)
x <- subset(ru.2009, mcond=="TC6" & tcond=="TS2")
## compute det statistics
d <- det(x)
summary(d)
## and plot results
plot(d, main="RU TC6 TS1 primary submission EVALITA 2009")

davidavdav/sretools.R documentation built on May 14, 2019, 10:37 p.m.