2004 February 26 Thursday
Voice Stress Lie Detectors Do Not Work

Hand-held lie detectors appear to be useless.

"We tested one of the more popular voice-stress lie detection technologies and got dismal results, both in the system's ability to detect people actually engaged in deception and in its ability to exclude those not attempting to be deceptive," said Mitchell S. Sommers, an associate professor of psychology in Arts & Sciences at Washington University in St. Louis.

"In our evaluation, voice-stress analysis detected some instances of deception, but its ability to do so was consistently less than chance you could have gotten better results by flipping a coin," Sommers said.

Sommers' research was supported by and conducted in conjunction with the Department of Defense Polygraph Institute (DODPI), located in Fort Jackson, S.C. Findings were presented at the World Congress of International Conference of Psychophysiology in July 2002. An academic paper on the study is under review for journal publication.

Sommers' study assessed the ability of Vericator, a computer-based system that evaluates credibility through slight variations in a person's speech, to detect deception in a number of different scenarios. Participants were questioned using different forms of interrogation and under conditions inducing various levels of stress.


"Voice-stress analysis is fairly effective in identifying certain variations in stress levels in human speech, but high levels of stress do not necessarily correlate with deception," Sommers said. "It may someday be possible to refine voice-stress analysis so that it is capable of distinguishing among various sources of stress and accurately identifying those that are directly related to deception. However, all the research that I've seen thus far suggests that it's wishful thinking, at best, to suggest that current voice-stress analysis systems are capable or reliably detecting deception."

My guess is that a high resolution image processing system that analyzed facial muscle changes would have a better chance of working. Take Paul Ekman's research into his Facial Action Coding System (FACS) and develop an automated means of using it and it might be possible to build a useful lie detector.

By Randall Parker at 2004 February 26 11:35 AM  | TrackBack

The lie-detector story reminds me of an episode of Barney Miller (1970's detective sitcom). Stoic Detective Dietrich confronts an overzelous lie-detector specialist (who thinks the device flawless) with a series of tests for the machine. If memory serves the exchange went something like this:

Specialist: What is your name?
Dietrich: Detective Arthur Dietrich.
Specialist: What is your social security number?
Dietrich: 548-85-9562
Specialist: Where were you born?
Dietrich: On the planet of Zordor, in a galaxy far, far away.

The line of questioning continued in the same vein and the specialist got spooked (for after all the machine was right and the Detective an alien) and ran away. Sorry for the long post but I cracked up upon that recollection...

Posted by: Michael Motherway on February 27, 2004 09:12 AM

Just too completely derail whatever chance this thread had to do with the post, Barney Miller was (and possibly still is) considered by most cops to be the most accurate cop show on TV.

Posted by: Alex on February 27, 2004 12:56 PM
Post a comment

Email Address:



Remember info?

Go Read More Posts On ParaPundit
Site Traffic Info
Popdex Citations