Layered Voice AnalysisA Prime Tool of Obama’s New National Security Army

The tool will be used to interrogate millions of white people to ascertainwhether they could be a racist threat or might intend to carry out a racistcrime. It is intended to prevent racist crime by incarcerating potential or

would-be racial criminals in the new Re-education Labor Camps.

Voice-stress analysis, an alternative to the polygraph as a method for liedetection, is already widely used in police and insurance fraudinvestigations. Now, however, it is being touted as a powerful and effectivetool for an array of new applications — everything from the screening ofpotential terrorists in the nation's airports to catching wayward spouses inmessy marital disputes.

Despite its booming popularity, a number of federally sponsored studieshave found little or no scientific evidence to support the notion that existingvoice-stress technologies are capable of consistently detecting lies anddeceptions.

Photo by Joe Angeles /WUSTL Photo

The Truster hand-held"Emotion Reader" is one ofmany commercial products

"We tested one of the more popular voice-stress lie detection technologies and gotdismal results, both in the system's ability todetect people actually engaged in deceptionand in its ability to exclude those notattempting to be deceptive," said Mitchell S. Sommers, an associateprofessor of psychology in Arts & Sciences at Washington University in St.Louis.

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

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

Sommers' study assessed the ability of Vericator, a computer-basedsystem that evaluates credibility through slight variations in a person'sspeech, to detect deception in a number of different scenarios. Participantswere questioned using different forms of interrogation and under conditionsinducing various levels of stress.

In one scenario, for example, participants were questioned about a mockcrime that they had witnessed but voice analysis correctly identifieddeception in only about 24 percent of individuals who were beingdeceptive. It also incorrectly identified deception among 18 percent of non-deceivers. In another experiment, Sommers induced high levels of stressby having participants play a video game that got increasingly difficult.Although none of the participants in this study were deceptive, Vericatorstill indicated that about 20 percent of the individuals were lying.

"Voice-stress analysis is fairly effective in identifying certain variations instress levels in human speech, but high levels of stress do not necessarilycorrelate with deception," Sommers said. "It may someday be possible torefine voice-stress analysis so that it is capable of distinguishing amongvarious sources of stress and accurately identifying those that are directlyrelated to deception. However, all the research that I've seen thus far

that claim to detect lies anddeception using voice-stressanalysis.

Download

suggests that it's wishful thinking, at best, to suggest that current voice-stress analysis systems are capable or reliably detecting deception."

In theory, voice-stress analysis works by measuring slight inaudiblefluctuations in the human voice known as "micro-tremors." Voice-stressanalysis systems, which generally include a microphone, tape recorder andrelated computer analysis equipment, are designed to recognize micro-tremor patterns that indicate when a speaker delivers words under stress,and specifically when those moments of stress are generated by anattempt to lie or deceive. Voice patterns are analyzed, graphed anddisplayed on a computer screen.

Various distributors of voice-stress analysis systems suggest that recentadvances in the technology, such as layered voice-stress analysis, haveelevated voice-stress lie detection to new levels of dependability andeffectiveness. Some suggest that the dismal performance of voice-stressanalysis lie detection in recent federal studies can be attributed to impropertest conditions or to tests being conducted using outdated and inferiorversions of the technology. Still, while many governmental investigative,military and law enforcement agencies have expressed an eagerness tofind a credible new means of lie detection, study after study has failed toyield strong scientific evidence in support of the technology.

Other reports, research on validity of voice-stress analysis liedetection:

"A review of the literature revealed that there have been no scientificstudies conducted, to date, to measure the validity of the computer stressanalyzed to detect deception," concluded a November 2003 study by theVirginia Department of Professional and Occupational Regulation. "It hasbeen argued that the computer stress analyzer is more cost effective,convenient, and more user friendly than the traditional polygraphequipment, however, one question still remains unanswered: how reliableis the equipment in its actual ability to detect, measure, and displaychanges in voice frequency? Has it ever been scientifically measured? Theanswer to this question is 'no.'"

Similar conclusions were reached in "Voice Stress Devices and theDetection of Lies," an overview of current voice-stress technologies written

by Donald J. Krapohl, Andrew H. Ryan and Kendall W. Shull; andpublished in Policy Review, the official publication of the InternationalChiefs of Police National Law Enforcement Policy Center.

The American Polygraph Association offers an online overview onunderstanding "Truth v. Myth" when it comes to comparing voice stress andpolygraph technologies.

Selected news coverage of voice-stress lie detectiontechnologies/controversies:

"Called Ex-Sense Pro, the V software measures voice for a variety ofparameters including deception, excitement, stress, mental effort,concentration, hesitation, anger, love and lust," according to a Jan. 16,2004, article in the engineering trade journal EE Times.

"It may sound like a joke from a secret agent television parody like 'GetSmart' or an Austin Powers movie, but the time has arrived for 'VoiceAnalysis Eyeglasses.' And it's no laughing matter," according to a Jan. 25,2004, article on the Israeli21c news site. An Associated Press story fromthe Las Vegas Consumer Electronics show suggests the "truth specs" willbe available in early 2004 at a cost of $400-$500.

Voice-stress analysis technology, an anti-fraud weapon said to be used insecret by some U.S. insurers, may soon get a public debut in New Mexico,according to an article in the Oct. 20, 2003, issue of National Underwriter,an insurance industry trade journal. Daniel Hays, associate editor, reportsthat the state superintendent of insurance is considering the use of voice-stress analysis in a national center processing insurance claims.

"Police Use of Voice Stress Analysis Generates Controversy," by MargieWylie, Newhouse News Service.

"Court TV's" Christina Lewis asks: "Is this lie detector telling the truth?"

A Jan. 10, 2004, newspaper article in the North California Times suggestsvoice-stress analysis offers a low-cost option for settling marital disputes.The article reports that a Chicago-based company has sold more than5,000 "Handy Trusters" in the past year, although a spokesman for thecompany couldn't identify any scientific research that has been conductedto verify the company's claim of an "84 percent accuracy rate." An online

version of this news article carried a related advertisement for "Truster LieDetector, Free shipping anywhere in the world, Portable and Accurate:http://trusters.com."

"A company called V-Entertainment is bringing voice-analysis technology toconsumers. It's a technology that's been used in the security and defensefields for some time, but now it's available to you and me," according to anonline news report by KLAS-TV, Las Vegas, Nev.

Web links for several manufacturers/distributors of voice-stress lie-detection systems:

The National Institute for Truth Verification (NITV), West Palm Beach, Fla.,manufactures and distributes the Computer Voice Stress Analyzer™(CVSA™), which was introduced in 1988. The company's Web sitesuggests the system is used by more than 1,400 law enforcement clients.

NEMESYSCO, based in Zuran, Israel, manufactures a wide range of"layered voice analysis" lie detection systems for security, fraud detection,pre-employment screening and consumer entertainment use. Productsrange from high-end anti-terrorism screening systems to the $19.99 "Love-Detector for Pocket PC" — "a tool that can tell you whether the person youare talking to really loves or cares for you." NEMESYSCO suggests that itis the originator of technologies behind the The Vericator™ and TheTruster™ brands of voice-stress analysis systems; but claims thesetechnologies are now obsolete.

V, located in New York and several other U.S. cities, is the exclusivedistributor for North America of the NEMESYSCO Layered Voice Analysistechnology (LVA), which V describes as the most sophisticated truthdetection technology available today. V's Web site suggests markets forLVA technologies "include homeland security, law enforcement and thebusiness community, including insurance and banking, wherever knowingwhether someone is telling the truth matters."

Layered Voice Analysis not only detects deception and truthfulness, butalso:Inaccuracies, high stress, high thinking level, high excitement, and overallpsychological state of the subject being interviewed.

• Our software does not profile/discriminate against any class of test-subject

• Our software requires no special equipment (just a laptop andmicrophone)

Vet TerroristIntentions

Investigative FocusTool

Discover HiddenThreats

Uncover InsuranceFraud

Laptop Technology Requirements

1. Minimum of 512MB RAM2. 2 USB Ports- minimum3. Operating System: Microsoft Windows XP4. Software: recommendation MSWord5. Updated service pack.6. Sound Card7. IBM computers are not accepted (sound card issues)

LVA 6.50 Level I Training OverviewLVA 6.50 Level I Training requires the participant to successfully completea 40 hour classroom session. During this training, participants will have acombination of lecture, practice with hands-on applications and appliedstudy. At the conclusion of Level I Training, all participants will be given awritten examination, proficiency testing and be required to take an interviewon-line and analyze it in the off-line mode.Class ScheduleMonday –Thursday 8:30- 4:30 (or later)Friday 8:00 to 2:00TRAINING ITINARY:Day 1:Introduction ……………………………………………………….....2 HoursLVA 6.50 and overview of On-line, Off-Line and Recorder ModesOverviewDetecting Deceptions in the Human VoiceLVA 6.50, Log-in and Main Screen…………………………………2 HoursProperly connecting Telephones/Microphones

Features of the Main ScreenIntroduction to LVA 6.50 On-Line Mode……………………..……..4 HoursOverview and Introduction to On-Line Mode (live interview)Hands-On Use and Practice of the On-Line ModeHomework…………………………………………….…………...1-2 HoursDay 2:LVA 6.50 On-Line Mode…………………………………………….4 HoursLearning On-Line and System MessagesUse of the Advanced FeaturesReading Your ResultsHands-On Use of the On-Line ModeIntroduction to LVA 6.50 Off-Line Mode…………………………...4 HoursHow to Segment sound filesIntroduction to Interpretation of resultsDealing with Mixed SegmentsHomework……………………………………………………………2 HoursDay 3:Off-Line Mode…………………….…………………………………8 HoursHomework OverviewUnderstanding how LVA 6.50 works technicallyReading Results: Show Segments, Graphs, Final ReportMarking RelevanceDay 4:LVA 6.50 Off-Line……………………………………………...……2 HoursHomework reviewOff-Line Q&AMerge and submerge segmentsLVA 6.50 Advanced Recorder Feature………………………...…….2 HoursHow to make a wave file from a sound source.Student Interviews with Live Individuals……...……………...……...4 HoursOff-Line analysis of InterviewsHomework………………………………………………………...….2 HoursDay 5:Review of Student On-Line/Off-Line Interviews……………......…1.5 HoursReview: Creating Your Own Wave or Test File…………..…..…...2-3 HoursLVA 6.50 Information Saving and RetrievalExporting and Importing Wave FilesWritten Examination…………………………………………….....2-3 HoursProficiency Testing Off-LineTOTAL: 40+ HOURS

LVA 6.50 Level II Training OverviewLVA 6.50 Level II Training requires the participant to successfully completea 40 hour classroom session. During this training, participants will have acombination of lecture, practice with hands-on applications and appliedstudy. At the conclusion of Level II Training, participants will be certifiedas Layered Voice Analysis operators.Class ScheduleMonday –Thursday 8:30- 4:30 (or later)Friday 8:00 to 2:00TRAINING ITINARY:Day 1:Introduction ……………………………………………………….....1 HoursLVA 6.50 and overview of On-line review…………………………..4 HoursAdvanced FeaturesInterpretation of readingsLVA 6.50 Hidden Windows…………………………………..……..3 HoursHands-On Use and Practice of Hidden WindowsHomework…………………………………………….…………...1-2 HoursDay 2:LVA 6.50 Off-Line Mode……………………………….…..……….8 HoursUse of the Advanced FeaturesReading Your ResultsAdvanced Analysis- Deception PatternsDealing with Merge and SubmergeHomework……………………………………………………………2 HoursDay 3:LVA 6.50 Off-Line Homework review ………………………...……1 HoursNeurolinguistics………………….……………………..…….………7 HoursHomework……………………………………………………………2 HoursDay 4:Student Interviews with Live Individuals……...……………...……...8 HoursOff-Line analysis of InterviewsHomework………………………………………………………...….2 HoursDay 5:Review of Homework and Investigation Interpretations……......…2-3 HoursReview: Exporting and Importing Wave Files

Profile of a Successful Interview/Interviewer………..………….....2-3 HoursTOTAL: 40+ HOURS

Layered Voice Analysis 6.50 Pricing Schedule

Layered Voice Analysis (LVA 6.50): $14,500Includes:o Training Level I and II for one individual (each training is 1 week

long and both must be completed within one year) Software and installation

o Software will be installed on your Laptop (IBM not accepted)o HASP (key to drive LVA 6.50 software), Microphoneo HASP renewal, technology support, updates on all new

versions of Layered Voice Analysis software, and analysissupport for one year after purchase date.

*You may also purchase a laptop from VAT as part of the package for$1000.00 (approximate).

Layered Voice Analysis Yearly License Renewal Fee: $1,500Includes:

o HASP renewal, technology support, updates on all newversions of Layered Voice Analysis software, and analysissupport for one year.

Additional Layered Voice Analysis Training: $1,500 perperson/per weekIncludes:

o LVA 6.50 Training: Each Level is 1 week long. Training is inMadison, WI (expenses of travel are not included).

Case Analysis Hourly Rate(VAT offers case analysis on pre-recorded material)

o Under 60 minutes of recording- $100 minimumo Hourly Rate: to be determined

“You Betcha” (Wink)