We suppose it depends on your level of paranoia whether you view the inability of government computers to listen to recordings of confusing party conversation muddle and pick out individual voices for special scrutiny a "Problem." But however your personal opinion on the matter falls, some researchers are claiming to have finally solved the "Cocktail Party Problem," which has befuddled scientists and snoops throughout the ages. The basic gist of the idea is that while a human can easily stand in the midst of a myriad of conversations and identify and follow each speaker individually, automated computer processing couldn't replicate this ability until now without having as many microphones as there were sound sources. Now a pair of University of Missouri-Columbia students are claiming victory over the problem using the "neural net" technique. In much the same way a human has natural abilities and responses to situations without exactly knowing why or how, the computer is trained through repetitive exposure to inputs (muddled sound) and outputs (single sources) until the computer figures out its own method for distinguishing -- though the actual process is still a tad mysterious. Of course, with the NSA involved and partially funding the project, they probably wouldn't have it any other way.