__NOTOC__ Some documentation for the Language ID codebase!
Where / how are the various metrics being calculated?
Theta for the operating point comes from thetasweep.pl on OUTCOMESTRAIN in the makefile Based on theta and outcomes score for each model on each file, resultbuilder.pl makes hard decisions. These are placed in NIST_RESULT_FILE. blddetcurve.sh script invokes splittargets.pl to split target from non-target. Given that split, hd_dcf from detware produces the coordinates of the operating point in hd.points. The point represented by hd.points is plotted as a star. The value of the DCF computed at the operating point should be found in metric.txt if you build the 'metric' target.
DET_nist.points is created as a sideeffect of running 'plot' from detware. The values of the second and third columns of the first row of DET_nist.points are placed in cdet.points. This contains the coordinates of the point on the det curve with min DCF. The point represented by cdet.points is plotted as a circle.
DET_nist.points is created as a sideeffect of running 'plot' from Detware. The value at the second column of the second row of DET_nist.points is extracted and placed in eer.points. The value at the first column of the second row of DET_nist.points is extracted and placed in eer.txt. This is the value of the DCF @ the EER point. The point represented by eer.points is plotted as a box.
Calculated by running average.pl on the output of printfirstcolumn.pl when it is run on the DET_nist.points files in all language directories at once. Stored in avgcost.txt.
Calculated by running average.pl on the eer.txt files in all language directories at once. Stored in avgeer.txt.
The various scripts utilized by the system.