next up previous contents index
Next: Recommendations Up: Forensic applications Previous: Spectrographic method

Semi-automatic method

 

It is clear that some of the research carried out in automatic speaker recognition  is targeted towards forensic applications. Most of the methods described in the previous chapter could be adapted to this goal, especially text-independent ones. However, if they offer a certain rate of success (under restrictive conditions), it must be stated clearly that they are far from being faultless, and that the consequence of an erroneous decision can be dramatic. Actually, since some expertises use very basic statistical methods (such as mean and variance computation), there does not seem to be any elaborate speaker recognition  system publicly used for forensic applications, but the possibility is not excluded given the degree of secrecy surrounding such applications. Nor is it excluded that experts resort to such systems for making their own decisions, with or without saying it explicitly. It is clear that such systems, whatever level they are used at, should be submitted to objective test protocols designed in agreement with members of the scientific community. Frequent contacts between speech researchers and members of the judiciary and the police would also certainly help to clarify the possibilities and the limits to the use of speech and of speech technology in forensic applications.




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