In forensic casework, the application of automatic speaker verification (SV) aims to determine the likelihood ratio of a suspect being vs. being not the speaker of an incriminating speech recording. For that purpose, the likelihood of the anti-speaker has to be estimated from the speech of an adequate number of other speakers. In many cases, speech signals of such an anti-speaker population are not available and it is generally too expensive to make an appropriate collection.

This paper presents a practical procedure of forensic SV which is based on a text-dependent SV system and instead of an anti-speaker population, a special speech database is used to calibrate the valuation scale for an individual case.