Dear where4,
You are right to observe that there has lately been a wave of
consumer-oriented lie-detection products based on voice analysis. My
research shows that most of these are based in fact or in claim on the
technology developed by the Israeli firm Nemesysco, although they are
marketed and resold under various names worldwide, including those you
have mentioned.
Before I describe these voice-analysis lie detectors in detail, let me
point out that the term "lie detector" has traditionally been applied
to a machine known as the polygraph. In many jurisdictions in the United
States, polygraph examinations are administered by certified experts on
behalf of police agencies but are inadmissible in court.
"In the United States, there is a double standard when it comes to the
use of polygraphs. Although the so-called lie detector is considered
an important law enforcement tool, polygraph data are inadmissible as
evidence in a court of law. The U.S. Supreme Court forbade private
companies from using them to screen job applicants, but allowed the
government to use them for the same purpose."
Washington Post: TechNews: "Lie-Detecting Devices: Truth or Consequences?"
http://www.washingtonpost.com/ac2/wp-dyn/A31229-2002Aug17?language=printer
A polygraph is a complex machine that measures several kinds of human
physiological response in the course of an interview. These measurements
mean little in themselves, and must be interpreted by the polygraph
operator.
"A polygraph or lie detector is a device which measures and records
several physiological variables such as blood pressure, heart rate,
respiration and skin conductivity while a series of questions is being
asked, in an attempt to detect lies. A polygraph test is also known as
a psychophysiological detection of deception (PDD) examination.
"A typical polygraph procedure starts with a pre-test interview designed
to establish a connection between the tester and the testee and to
gain some preliminary information which will later be used for control
questions (see below). Then the tester will explain the polygraph,
emphasizing that it can detect lies and that it is important to answer
truthfully. Then a "stim test" is often conducted: the testee is asked
to deliberately lie and then the tester reports that he was able to
detect this lie. Then the actual test starts. Some of the questions
asked are irrelevant ("Are you 35 years old?"), others are "probable-lie"
control questions that most people will lie about ("Have you ever stolen
money?") and the remainder are the relevant questions the polygrapher is
really interested in. The different types of questions alternate. The
test is passed if the physiological responses during the probable-lie
control questions are larger than those during the relevant questions. If
this is not the case, the tester attempts to elicit admissions during
a post-test interview ("Your situation will only get worse if we don't
clear this up"). These admissions are the main goal of the test.
"The accuracy of polygraph tests is a matter of considerable
controversy. While some claim the test to be accurate in 70% - 90% of the
cases, critics charge that rather than a "test", the method amounts to
an inherently unstandardizable interrogation technique whose accuracy
cannot be established. Polygraph tests have also been criticized for
failing to catch actual spies such as Aldrich Ames, who passed two
polygraph tests while spying for the Russians.
"Several countermeasures designed to pass polygraph tests have been
described; the most important of which is never to make any damaging
admissions. Additionally, several techniques can be used to increase
the physiological response during control questions. In an interview,
Ames was asked how he passed the polygraph test. His response was that
when told he was to be polygraphed he asked his Soviet handlers what to
do, and was quite surprised that their advice was simply to relax when
being asked questions, which he did."
Wikipedia: polygraph
http://en.wikipedia.org/wiki/Polygraph
It appears, then, that a subject who knows he is to undergo a
polygraph examination and who prepares for it properly can deceive the
operator. Proponents of the polygraph, who are most numerous in the
United States, argue the contrary. They do admit that a polygraph does
not measure voice response, which is known to be one of the clearest
subjective indicators of lying. The American Polygraph Association claims
that voice response cannot be measured on a scientific basis.
"A typical polygraph examination will include a period referred to
as a pre-test, a chart collection phase and a test data analysis
phase. In the pre-test, the polygraph examiner will complete required
paperwork and talk with the examinee about the test. During this period,
the examiner will discuss the questions to be asked and familiarize
the examinee with the testing procedure. During the chart collection
phase, the examiner will administer and collect a number of polygraph
charts. Following this, the examiner will analyze the charts and render
an opinion as to the truthfulness of the person taking the test. The
examiner, when appropriate, will offer the examinee an opportunity to
explain physiological responses in relation to one or more questions
asked during the test. It is important to note that a polygraph does not
include the analysis of physiology associated with the voice. Instruments
that claim to record voice stress are not polygraphs and have not been
shown to have scientific support."
American Polygraph Association: Frequently asked questions about Polygraph
http://www.polygraph.org/faq.htm
The American Polygraph Association recommends four manufacturers
of polygraph equipment: Axciton, Lafayette Instrument, Limestone
Technologies, and Stoelting.
Axciton Systems: Products
http://www.axciton.com/Prod.html
Lafayette Instrument: Conventional Polygraphs
http://www.lafayetteinstrument.com/conventi.htm
Limestone Technologies: Hardware
http://www.limestonetech.com/hardware.php
Stoelting
http://www.stoeltingco.com/
The polygraph devices sold by these manufacturers are unwieldy, requiring
at least a suitcase to carry, and rather expensive. Regardless of their
value as lie-detecting instruments, consensus holds that they are useless
in the hands of anyone but a trained expert. Thus, they are no good to
a layman such as you or me.
"The American Polygraph Association believes that scientific evidence
supports the high validity of polygraph examinations. Thus, such
examinations have great probative value and utility for various uses
in the criminal justice system. However, a valid examination requires
a combination of a properly trained examiner, a polygraph instrument
that records as a minimum cardiovascular, respiratory, and electrodermal
activity, and the proper administration of an accepted testing procedure
and scoring system."
American Polygraph Association: Validity & Reliability of Polygraph Testing
http://www.polygraph.org/validityresearch.htm
The following article by respected technologist Andrew Kantor cites
studies carried out by the American Medical Association and the TV program
"60 Minutes" suggesting that polygraphs are inaccurate even in the hands
of a trained operator.
"[On] the anti-polygraph side I found the American Medical Association,
the American Psychological Association, and 60 Minutes. They all found
essentially the same thing: Lie detectors show what the examiners want
them to show.
"In 1986, 60 Minutes demonstrated this rather dramatically. Using Popular
Photography magazine as a front, the producers hired several polygraphers
to help find someone who had, they were told, stolen hundreds of dollars
of photographic equipment. (No such theft had taken place.) Each examiner
was told that a different one of the 'suspects' was probably the guilty
party.
"Lo and behold, each polygrapher fingered the suspect they were told
ahead of time was probably guilty. Oops.
"An American Medical Association expert testified before Congress
that "the [lie detector] cannot detect lies much better than a coin
toss." Further, an article published in the Journal of the American
Medical Association by the AMA's Council on Scientific Affairs said
in part, "Though the polygraph can recognize guilty suspects with an
accuracy that is better than chance, error rates of significant size
are possible." Ouch.
"A 1997 survey by the American Psychological Association found that
psychologists feel that "The use of the polygraph (lie detector test)
is not nearly as valid as some say and can easily be beaten and should
never be admitted into evidence in courts of law." Eek."
USA Today: Andrew Kantor: Lie detectors are likely lying
http://www.usatoday.com/tech/columnist/andrewkantor/2004-04-08-kantor_x.htm
It is clear where the interests of the American Polygraph Association
fall, so it is no surprise that they argue against the new lie-detection
technology based on voice analysis. Yet the premise of voice-analytic lie
detection is a perfectly natural one. When you attempt to deceive someone,
whether over the phone or in person, the most difficult thing to control
is your tone of voice. Your throat constricts, your upper lip trembles,
your mouth goes dry, and your voice quavers.
The systems sold by V-Entertainment in the United States are consumer
versions of a voice-analytic lie-detection algorithm developed by the
Israeli firm Nemesysco.
"A U.S. company using technology developed in Israel is pitching a
lie detector small enough to fit in the eyeglasses of law enforcement
officers, and its inventors say it can tell whether a passenger is a
terrorist by analyzing his answer to that simple question in real-time.
"The technology, developed by mathematician Amir Lieberman at Nemesysco
in Zuran, Israel, for military, insurance claim and law enforcement use,
is being repackaged and retargeted for personal and corporate applications
by V Entertainment (New York). [...]
"The heart of Nemesysco's security-oriented technology is a
signal-processing engine that is said to use more than 8,000 algorithms
each time it analyzes an incoming voice waveform. In this way it detects
levels of various emotional states simultaneously from the pitch and
speed of the voice.
"The law enforcement version achieved about 70 percent accuracy in
laboratory trials, according to V Entertainment, and better than 90
percent accuracy against real criminal subjects at a beta test site at
the U.S. Air Force's Rome Laboratories.
""It is very different from the common polygraph, which measures changes
in the body, such as heart rate," said Richard Parton, V's chief executive
officer. "We work off the frequency range of voice patterns instead of
changes in the body." The company said that a state police agency in
the Midwest found the lie detector 89 percent accurate, compared with
83 percent for a traditional polygraph."
Electrical Engineering Times: Lie-detector glasses offer peek at
future of security
http://www.eetimes.com/story/OEG20040116S0050
Assuming these studies did take place as reported, and considering that
the technology is based on legitimate signal-processing algorithms,
it seems that the premium V-Entertainment products are indeed useful in
antagonistic interviews.
It is also reassuring to see that Nemesysco describes its own invention,
the LVA chip, in realistic terms.
"Professionals in the field of lie detection know that there is no
such thing as a "real" lie detector, as lying is not a unified set of
feelings. Lying is a result of a deep logical process that has intention
behind it. One will lie to protect himself from harm, while another will
lie to gain profit, or even just to make a joke. Due to this, there is
no fixed set of characteristics (physiological or psychological) that
differentiate lies from truth. However, LVA is capable of detecting the
intention behind the lie, and by so doing can lead you in identifying
and revealing the lie itself. This functionality brings LVA as close as
you can possibly get to a "real" lie detector."
Nemesysco: The LVA (Layer Voice Analysis) Technology
http://www.nemesysco.com/technology-lvavoiceanalysis.html
Finally, given that Israeli security agencies are renowned for their
interrogation expertise, I am persuaded that the core Nemesysco technology
has some value when used by the right hands in the right situation.
I am equally convinced, however, that the many budget-priced spin-offs
of the Nemesysco technology circulating around the Internet are little
more than toys. All of these products are similar in appearance, and
every firm claims either a direct connection with Nemesysco or implies
that it uses their voice-analysis technology. Some distributors carry
versions for PC and Pocket PC that strongly resemble those marketed by
V-Entertainment, but most carry a small, cheap device known generally
as the Truster or Handy Truster.
Love Detector: Products
http://www.love-detector.com/community.html
ex-Sense: Products
http://www.ex-sense.com/products.html
911 Tech: Product
http://www.911.co.kr/truster_01_eng.html
Clearance: Handy Truster
http://www.clearance.net/store/customer/product.php?productid=44369&partner=gg
All of these gadgets have in common the LED screen showing an apple that
gets consumed by a worm as the subject's lies supposedly worsen. They
look like fun, but I would not trust them in any kind of important
situation. All the reports I have found indicate that their accuracy is
slight at best.
"While high-end professional models range from $1,000 to $20,000, there
are devices for as little as $19.95.
"Truths told to the gimmicky Handy Truster produce an apple on the
machine's screen, while lies produce a worm; 911 Tech Co., which
manufactures the gadget, says it has sold 20,000 a year for the past
few years.
"The slightly more sophisticated Truster software program that runs on a
desktop computer gives text ratings of truthfulness. The companies that
market these technologies say they are more than 80 percent accurate.
"Rick Garloff, a 35-year-old who lives in Galt, Calif., is
skeptical. Still, he said, even if the systems are not great lie
detectors, they are wonderful lie deterrents."
Washington Post: TechNews: "Lie-Detecting Devices: Truth or Consequences?"
http://www.washingtonpost.com/ac2/wp-dyn/A31229-2002Aug17?language=printer
"In very anecdotal testing among LabRats in the TechTV Labs, we had mixed
results. In some cases, the Truster did a pretty good job when LabRats
were asked simple true and false questions. Often, after being asked to
choose a number between one and 10, subjects' stress levels rose as the
inquirer zeroed in on their numbers. However, truthfulness and stress
were shown to be minimal on the device when the subjects were asked more
complicated questions."
TechTV: Truster Emotion Reader
http://www.g4techtv.com/freshgear/features/30208/Truster_Emotion_Reader.html?
The fact that these devices have been around for several years prior
to the introduction of Nemesysco's consumer technology suggests to
me that they are belatedly trying to cash in on the Israeli firm's
reputation. I would not buy such a gadget for anything but amusement,
and I don't think I would pay more than $20 for it.
Since V-Entertainment does, in fact, market the genuine Nemesysco
technology, I would consider purchasing only from them. I would certainly
be far more interested in one of their voice-analytic lie detectors
than in a polygraph, which requires a trained operator and appears to
be mostly fraudulent anyway.
I enjoyed researching the subject of lie detectors on your behalf. Should
you find that any part of my answer requires correction or elaboration,
do let me know through a Clarification Request so that I have a chance
to fully meet your needs before you assign a rating.
Regards,
leapinglizard |
