posted 06-19-2010 02:58 PM         

The Truth Hurts
Scientists question voice-based lie detectionBy Rachel Ehrenberg July 3rd, 2010; Vol.178 #1 (p. 28) Text Size
Enlarge
The truth hurts
Many police forces have turned to voice-based lie detectors, but scientists are finding that these polygraph alternatives don't reliably tell fact from fiction. Michael MorgensternTruster-Pro and the Vericator may sound like devices Wile E. Coyote would order from the Acme Co., but they are real technologies for detecting lies. Unlike the traditional polygraph, which zeroes in on factors such as pulse and breathing rate, these analyzers aim to assess veracity based solely on speech.

Police departments shell out thousands of dollars on such devices — known collectively as voice stress analyzers — in an attempt to tune in to vocal consequences of lying. Airports are considering versions for security screening purposes, and insurance companies may employ the polygraph alternatives to detect fraud.

But beyond their crime-fighting objective, these tools have something less noble in common with their predecessor: a poor track record in actually telling truth from deception.

Scientists evaluating Truster-Pro, the Vericator and newer analyzer models repeatedly report lackluster results. Now research finds that two of the most commonly used voice stress analyzers can discern lies from truth at roughly chance levels — no better than flipping a coin.

“Quite frankly, they’re bogus. There’s no scientific basis whatsoever for them,” says John H.L. Hansen, head of the Center for Robust Speech Systems at the University of Texas at Dallas. “Law enforcement agencies — they’re spending a lot of money on these things. It just doesn’t make sense.”

A lackluster alternative

Many agencies have been seeking alternatives to the polygraph, especially following a 2003 National Research Council report that concluded that the physiological responses measured, such as increased heart rate, can identify stress but not pinpoint deception. Champions of voice stress analyzers often cite this report among other criticisms of polygraphs as a reason to switch to voice-based lie detection. The National Institute for Truth Verification — a company based in West Palm Beach, Fla., that makes a widely used device called the Computer Voice Stress Analyzer — has a page on its website dedicated to denigrating this traditional lie detector, titled “Polygraph Failures Continue to Mount.”

But the institute fails to mention the same report’s conclusions about alternatives to the polygraph, including voice analyzers. Research offers “little or no scientific basis for the use of the computer voice stress analyzer or similar voice measurement instruments as an alternative to the polygraph for the detection of deception,” the report noted.

As with the old lie detector, creators of voice analyzers usually avoid direct claims that the units detect deception, speech perception expert James Harnsberger said in April in Baltimore at a meeting of the Acoustical Society of America. Instead, the developers contend that physiological changes that occur when someone is lying trigger consistent, readable changes in voice. “There’s an assumption that there’s a direct mind-mouth link,” said Harnsberger, of the University of Florida in Gainesville.

Speech does in fact change when a person is under stress, both in frequency and in the amount of time spent on segments of words, says Hansen. But, as with the polygraph, distinguishing stress related to deception from stress related to fatigue, anxiety or fear is not so easy.

“No one has identified an acoustic signature that is unique to deception,” says Mitchell Sommers, director of the Speech and Hearing Laboratory at Washington University in St. Louis.

Two large studies, one conducted in a jail and another in a lab, suggest that the two most widely used voice stress analyzers haven’t pinpointed such a signature, either.

One voice analyzer — Layered Voice Analysis, created by the Israel-based company Nemesysco — purports to use more than 8,000 algorithms to tune in to three states of mind: excitement, stress and cognitive dissonance (the psychological discomfort that comes with holding two conflicting views at once). A second, the Computer Voice Stress Analyzer, claims to detect inaudible changes in “microtremors” in the voice of a lying person. Versions of both systems can cost more than $10,000 with training.

Numbers speak truth

In the jailhouse study, researchers led by Kelly Damphousse of the University of Oklahoma in Norman interviewed a random sample of 319 arrestees during booking in an Oklahoma county jail. The team asked the men about recent use of drugs, including cocaine, marijuana, PCP and methamphetamine, and researchers dissected responses with both voice analyzers. After the interview, the arrestees’ urine was tested for actual drug use.

Both voice analyzers got poor marks, write Damphousse and his colleagues in a 2007 report for the Department of Justice. All told, fewer than one-sixth of the lies were detected. LVA spotted about 10 percent of lies, while CVSA got nearly 20 percent. They were better at detecting truths, correctly identifying between 85 and 95 percent. The remaining truths were still falsely labeled as lies.

The technologies didn’t fare much better in the lab, Harnsberger reported at the Acoustical Society meeting. As part of a team of Florida researchers, Harnsberger underwent training for both technologies. Working with company representatives, the researchers conducted a study where subjects were video recorded telling the truth and telling lies under various levels of stress. For a very high-stress lie, the participants were asked to make a statement that they strongly disagreed with; topics included sexual orientation and gun control. Participants were also told that the video would be shown to their peers and that they should expect an electric shock during the statement.

One technology caught lies at rates similar to chance, and the other did somewhat better, Harnsberger and colleagues reported at the meeting and in two papers in the Journal of Forensic Science. But both detectors also falsely labeled true statements as lies at similar rates. These false positives, which are often unreported in studies and left out of company descriptions of the technologies, are key for evaluating merit, Harnsberger noted.

“A common mistake is to only report how many lies were successfully detected,” Harnsberger says. “You could write ‘lie’ on a piece of paper and hold it up every time someone speaks to you, and you will detect 100 percent of the lies.”

Amir Liberman, CEO of Nemesysco, likens the technology to a microscope; it doesn’t detect disease per se, but it’s a tool for exploration. He adds that the circumstances and the interrogator are crucial to success. Still, Liberman says explicitly that Layered Voice Analysis can do what researchers say it can’t: “LVA differentiates between stress and lies,” he says. How exactly, he can’t disclose. The National Institute for Truth Verification declined requests for an interview.

Harnsberger has repeatedly made the case to policy makers that voice analyzers don’t live up to their manufacturers’ claims. And currently only two “credibility assessment” devices have been approved for use by the Department of Defense: the good old polygraph and a next-generation version that also evaluates physiological factors.

But manufacturers of the voice stress analyzers continue to lobby for their products, says Harnsberger. Such efforts may not be in vain. In a statement, Defense Department spokesperson René White said the department “continues to conduct research on and evaluate additional potential credibility assessment tools.” And according to USAspending.gov, the National Institute for Truth Verification, maker of the Computer Voice Stress Analyzer, has received more than $1.6 million in Defense Department contracts since 2005.

Though the technologies apparently don’t tell truth from fiction, they may have merit as props. The jailhouse study followed up work that had asked arrestees about drug use, that time without a lie detector in the room. Comparing the two studies revealed that more than three times as many drug users lied when no device was present than when one was.

posted 06-26-2010 07:45 PM         

Ted

Main | WFTV asks about Edwin: What happened in those two minutes! »

Claim that 14-year-old failed lie detector is bogus
Uncategorized — posted by mike thomas on June, 25 2010 1:34 PM
Discuss This: Comments(56) | Add to del.icio.us | Digg it You may have seen the blaring WFTV story about how Edwin McFarlane, the 14-year-old boy accused of trying to abduct a 3-year-old girl from a Burlington Coat Factory, failed a lie detector test.

Be careful what you believe.

The lie detector story broke the day before Edwin had a court hearing.

This was the headline on the station’s web site. ”WFTV Learns Arrested 14-Year-Old Failed Polygraph”

Let’s take a closer look at this claim.

The sheriff’s department, which administered the test, doesn’t even use a polygraph.

The department uses a voice stress analyzer.

Now let me introduce you to Richard Keifer. Among his credentials, he is the former FBI National Polygraph Program Manager and former President of the American Polygraph Association. Put another way, he is one of the nation’s foremost experts on lie detectors.

This is what he says about a voice stress analyzer: “It doesn’t work. The research of voice stress is that it is about as accurate as flipping a coin.’’

Keifer said that they worked with the machines at the FBI and no matter how hard they tried, they couldn’t figure out if someone was lying.

This is backed up by a December 2008 report apparently done for the Department of Defense, which reviewed 24 studies done over a period of 30 years.

They “failed to provide evidence of the validity or reliability of voice stress analysis-based technologies for the detection of deception in individuals,’’ the report said.

This is what a report prepared for the Department of Justice concluded: “Our research therefore complements previous research by failing to find support for the VSA products in a real world (jail) setting.”

Here is another good link.

A report from ABC News.

Good stuff here!

So what we seem to have here are detectives hooking up a very stressed teenager to their voodoo stress test machine, and proclaiming him a liar. And then this test mysteriously winds up in WFVT’s hands the day before the hearing, and Edwin is publicly proclaimed a liar, which makes him look quite guilty. It all makes you wonder what kind of case the detectives have against this kid, who it appears only committed the crime of dumbly trying to help a lost toddler find her mom.

Meanwhile, Sheriff Demings has said that all information from the investigation is confidential, and that the department will not discuss evidence. Is Demings curious at all about how and, more importantly why, this information leaked out right before a hearing.

posted 06-27-2010 08:45 AM            

I may send these to the Utah PDs that are using this prop. Donna

posted 06-27-2010 11:14 AM         

Ted

'Abduction' case against teen reaches new low with evil smear campaign

COMMENTARY

5:33 p.m. EDT, June 26, 2010
E-mail Print Share Text Size os-mike-thomas-edwin-arrest-062710-20100626

It is frightening to watch the power of the state unleashed to destroy a 14-year-old boy.

He is Edwin McFarlane, the bumbling teen whose attempt to help a 3-year-old girl find her mother June 10 at a Burlington Coat Factory has him facing a first-degree felony charge of false imprisonment.

The case never has made sense. And confronted with the possibility they made a mistake in a high-profile arrest, Orange County sheriff's detectives and now state prosecutors have waged a campaign to save face by distorting evidence and smearing the kid.

When I began questioning the arrest, the Sheriff's Office told me surveillance cameras proved Edwin never contacted his mother before leaving the store with the girl, as she claimed. I checked the videos and found this wasn't true.

Get more stories like this. Sign up for home delivery today.

After I printed that, WFTV-Channel 9 ran a story that said while the store tapes may not indicate Edwin did anything wrong, detectives were concerned about Edwin's actions with the girl when they were off-camera for two minutes in the store parking lot.

Where do these people go to detective school?

Edwin was out of camera range for less than 1:40 in the parking lot off West Colonial Drive. For all but about 20 seconds of that, his mother also was outside because she followed him. And during the time she wasn't outside, she said she was watching him from inside the store. That makes sense when you watch the video. As she walks outside, she doesn't look around for him. She looks in the direction he was headed.

Also, the toddler's mother went outside to retrieve her girl, so she was outside for about half the time Edwin was out of range of a surveillance camera.

So if Edwin committed some unseemly act, he would have had to do it very quickly in an open parking lot in the middle of the day and in full view of his own mother. That would make his mother an accomplice.

Edwin had no criminal history to explain any ill intent. So detectives delved into his school files where, lo and behold, he had a discipline record.

Look what happened next. Edwin was scheduled for a court appearance Thursday. Two days before, the Sentinel was notified by the State Attorney's Office of unspecified issues in Edwin's past. We were advised to be at the hearing.

The night before the hearing, WFTV-Channel 9 came out with a blockbuster story about Edwin's confidential school records, including a sexual incident that the station said may have been criminal. The station also reported that Edwin flunked a polygraph about the incident with the girl.

It would appear someone at the Sheriff's Office or State Attorney's Office was leaking information about a confidential juvenile case.

I subsequently discovered that Edwin was not given a polygraph test but a voice stress test. This is a technology that dozens of studies have repeatedly shown is no more accurate than a coin flip.

But the damage was done. Edwin would face the judge already branded as a sexual offender and liar.

At the hearing, Assistant State Attorney Teri Mills-Uvalle delivered as promised. She told Judge Thomas Turner that while the state wasn't ready to file charges, he should know that Edwin has 18 school-based disciplinary referrals, including three for sexually related incidents.

When she was done, Judge Turner delivered the equivalent of a judicial smackdown. He released Edwin from home confinement.

Undeterred, Mills-Uvalle then went outside the courtroom and proceeded to pile on in front of reporters.

She created the image of Edwin as some dangerous kid prone to sexual offenses. And then when pressed for details to back this up, she hid behind confidentiality rules.

What an evil thing to do to a 14-year-old boy.

Meanwhile, WFTV has come up with its own term for Edwin's transgressions: "Sexually charged conduct.''

That includes making an obscene gesture at another kid in class — a boy, by the way.

When it comes to sexually charged conduct, Edwin would have been a slacker in the Catholic school I attended. Back then the teacher blistered your backside. In this era of "zero tolerance," everything is documented in a disciplinary report.

Get more stories like this. Sign up for home delivery today.

It seems Edwin has behavior problems but there's been nothing to indicate he is anything close to a predator.

"If they had a trial, none of that would be admissible,'' said Don Lykkebak, a veteran defense attorney. "The only way you can get evidence of other misconduct in is if that conduct is similar behavior to what occurred in this case.''

Lykkebak called the state attorney's actions "not very professional.''

A spokesman for the State Attorney's Office, Randy Means, said even if prosecutors can't prove a case against a juvenile, the state still can "put sanctions on him if he does have a problem."

What? You can arrest a kid for one thing, then punish him for completely non-related, non-criminal acts you happen to dig up in his past?

Prosecutors are trying to intimidate Edwin's mother into accepting the juvenile equivalent of a plea bargain. It's about saving face. It's about adult egos being vested in bringing down a young teenager who apparently was only trying to do a good deed.

I doubt State Attorney Lawson Lamar spends an hour a month in his juvenile division.

But it's time he took a personal interest in this case and examined the evidence closely. If he thinks it proves Edwin intended to abduct that girl and cause her harm, then it's his duty to file charges.

If not, it's time to leave this boy and his mother alone.

Mike Thomas can be reached at 407-420-5525 or mthomas@orlandosentinel.com.