next up previous contents index
Next: Employing expert judgments to Up: Assessing speaker verification and Previous: Assessing speaker verification and

Sampling rare events in speaker verification and recognition systems

Section 9.2.5 contains examples about how many speakers are needed to be 95% certain that the proportion of men and women in the sample differs from that in the population by at most 4%. In this case, the events that were being dealt with (men and women) were equally frequent - p and q were the same at 0.5. If p is quite small as it may be in the case of impostors into speaker verification  systems (perhaps less than 1% of the users of a system), it would be necessary to obtain very large samples (running in to tens of thousands). In these cases the Poisson distribution has to be used to estimate sample sizes.




EAGLES SWLG SoftEdition, May 1997. Get the book...