Polygraph vs Voice Stress Analysers

Many people confuse voice stress analysis with polygraph examinations, mainly due to the fact that a large number of individuals offering voice stress analysis services mislead their client base by introducing themselves as polygraph examiners.

The major differences between Forensic Psycho Physiological Examinations (Polygraph) and Voice Stress Analysis are:

  • The first commercial polygraph examination was introduced by John Larson in 1921. Long before the existence of Voice Stress Analysis.
  • A polygraph instrument collects forensic data from at least three different systems in the human body ex. Respiratory Activity, Sweat Gland Activity and Cardiovascular Activity. Voice stress analysis records "microtremors" in the voice box.
  • Research field studies on the accuracy of polygraph have shown that when a well trained polygraph examiner who utilize an accredited polygraph testing procedure the accuracy in the 98% range is.

Research studies on the accuracy of voice stress analysis have found that the validity of voice stress was poor, that accuracy is not significantly greater than chance, that voice measures were not reliable or useful, that it is "almost as accurate as flipping a coin etc.

ABC had an interview with the inventor of CVSA “Dr” Humble to view the video click here

Discovery Channel’s Mythbusters set out to prove that the Polygraph could be beaten and were unable to do so. Click here to watch the video.

Below is a list of the university-grade research studies that have investigated voice stress as a deception detection approach. Some studies looked at the CVSA device in particular, while others investigated whether voice stress analysis in general could be used to detect stress or deception. Copies of these studies can be obtained at many university libraries.

Brenner, M., Branscomb, H., & Schwartz, G. E. (1979). Psychological stress evaluator: Two tests of a vocal measure. Psychophysiology, 16(4), 351-357.

Conclusion: "Validity of the analysis for practical lie detection is questionable"

 

 

The American Polygraph Association published on their Website, a list of studies, conducted between 1973 and 2006, to evaluate the accuracy of Voice Stress Analyses, as follows:

Device                               Research Sponsor                                  Year                                     Results


PSE
US Army

1973

No better than chance

 

US Army

1973

NO better than chance

PSE

Michigan State University

1978

No better than chance

 

Royal Ottawa Hospital (Canada)

1979

NO better than Chance

PSE

University of Oregon

1979

No better than chance

 

Michigan State University

1979

No better than chance

 

Ford Foundation/ Israeli Police

1980

No better than chance

PSE

Michigan State University

1983

No better than chance

 

Israeli Police

1985

No better than chance

 

U of Florida

1987

No better than chance

 

Kansas State University

1987

Unreliable

Mark Il

Texas Tech University

1990

No better than chance

CVSA

Department of Defense

1995

No better than chance

CVSA

Department of Defense

1996

No better than chance

CVSA

Department of Defense

1996

No better than chance

CVSA

Department of Defense

2000

Unreliable

Vericator

Department of Defense

2002

Low reliability/validity

Diogenes

Department of Defense

2002

Did not detect deception

Vericator

Department of Defense

2002

Did not detect deception

T rusterPro

Johannes Gutenberg University

2006

No better than chance

CVSA

Department of Defense

2006

No better than chance

LVA

Department of Defense

2006

No better than chance

CVSA

Department of Justice

2007

No better than chance

LVA

Department of Justice

2007

Low validity

In March 2008, the following article was published in the National Institute of Justice, which is the research development and evaluation agency of the United States Department of Justice.

“Voice Stress Analysis: Only 15 Percent of Lies About Drug Use Detected in Field Test
by Kelly R. Damphousse, Ph.D.
The products, manufacturers, and organizations discussed in this document are presented for informational purposes only and do not constitute product approval or endorsement by the U.S. Department of Justice.
Law enforcement agencies across the country have invested millions of dollars in voice stress analysis (VSA) software programs.[1] One crucial question, however, remains unanswered:
Does VSA actually work?
According to a recent study funded by the National Institute of Justice (NIJ), two of the most popular VSA programs in use by police departments across the country are no better than flipping a coin when it comes to detecting deception regarding recent drug use. The study's findings also noted, however, that the mere presence of a VSA program during an interrogation may deter a respondent from giving a false answer.
VSA manufacturers tout the technology as a way for law enforcers to accurately, cheaply, and efficiently determine whether a person is lying by analyzing changes in their voice patterns. Indeed, according to one manufacturer, more than 1,400 law enforcement agencies in the United States use its product.[2] But few studies have been conducted on the effectiveness of VSA software in general, and until now, none of these tested VSA in the field—that is, in a real-world environment such as a jail. Therefore, to help determine whether VSA is a reliable technology, NIJ funded a field evaluation of two programs: Computer Voice Stress Analyzer® (CVSA®)[3] and Layered Voice AnalysisTM (LVA).
Researchers with the Oklahoma Department of Mental Health and Substance Abuse Services (including this author) used these VSA programs while questioning more than 300 arrestees about their recent drug use. The results of the VSA output—which ostensibly indicated whether the arrestees were lying or telling the truth—were then compared to their urine drug test results. The findings of our study revealed:

  • Deceptive respondents. Fifteen percent who said they had not used drugs—but who, according to their urine tests, had—were correctly identified by the VSA programs as being deceptive.
  • Nondeceptive respondents. Eight and a half percent who were telling the truth—that is, their urine tests were consistent with their statements that they had or had not used drugs—were incorrectly classified by the VSA programs as being deceptive.

Using these percentages to determine the overall accuracy rates of the two VSA programs, we found that their ability to accurately detect deception about recent drug use was about 50 percent.
Based solely on these statistics, it seems reasonable to conclude that these VSA programs were not able to detect deception about drug use, at least to a degree that law enforcement professionals would require—particularly when weighed against the financial investment. We did find, however, that arrestees who were questioned using the VSA instruments were less likely to lie about illicit drug use compared to arrestees whose responses were recorded by the interviewer with pen and paper.
So perhaps the answer to the question "Does VSA work?" is . . . it depends on the definition of "work."
What Is VSA?
VSA software programs are designed to measure changes in voice patterns caused by the stress, or the physical effort, of trying to hide deceptive responses.[4] VSA programs interpret changes in vocal patterns and indicate on a graph whether the subject is being "deceptive" or "truthful."
Most VSA developers and manufacturers do not claim that their devices detect lies; rather, they claim that VSA detects microtremors, which are caused by the stress of trying to conceal or deceive.
VSA proponents often compare the technology to polygraph testing, which attempts to measure changes in respiration, heart rate, and galvanic skin response.
Even advocates of polygraph testing, however, acknowledge its limitations, including that it is inadmissible as evidence in a court of law; requires a large investment of resources; and takes several hours to perform, with the subject connected to a machine. Furthermore, a polygraph cannot test audio or video recordings, or statements made either over a telephone or in a remote setting (that is, away from a formal interrogation room), such as at an airport ticket counter. Such limitations of the polygraph—along with technological advances—prompted the development of VSA software.
Out of the Lab, Into the Field
Although some research studies have shown that several features of speech pattern differ under stress,[5], [6] it is unclear whether VSA can detect deception-related stress. In those studies that found that this stress may be detectable, the deception was relatively minor and no "jeopardy" was involved—that is, the subjects had nothing to lose by lying (or by telling the truth, for that matter). This led some researchers to suggest that if there is no jeopardy, there is no stress—and that if there is no stress, the VSA technology may not have been tested appropriately.[7]
The NIJ-funded study was designed to address these criticisms by testing VSA in a setting where police interviews commonly occur (a jail) and asking arrestees about relevant criminal behavior (drug use) that they would likely hide.[8]
Our research team interviewed a random sample of 319 recent arrestees in the Oklahoma County jail. The interviews were conducted in a relatively private room adjacent to the booking facility with male arrestees who had been in the detention facility for less than 24 hours. During separate testing periods, data were collected using CVSA®and LVA.
The arrestees were asked to respond to questions about marijuana use during the previous 30 days, and cocaine, heroin, methamphetamine, and PCP use within the previous 72 hours. The questions and test formats were approved by officials from CVSA® and LVA. The VSA data were independently interpreted by the research team and by certified examiners from both companies.
Following each interview, the arrestee provided a urine sample that was later tested for the presence of the five drugs. The results of the urinalysis were compared to the responses about recent drug use to determine whether the arrestee was being truthful or deceptive. This determination was then compared to the VSA output results to see whether the VSA gave the same result of truthfulness or deceptiveness.
Can VSA Accurately Detect Deception?
Our findings suggest that these VSA software programs were no better in determining deception about recent drug use among arrestees than flipping a coin.
To arrive at this conclusion, we first calculated two percentage rates[9]:

  • Sensitivity rate. The percentage of deceptive arrestees correctly identified by the VSA devices as deceptive.
  • Specificity rate. The percentage of nondeceptive arrestees correctly classified by the VSA as nondeceptive.

Both VSA programs had a low sensitivity rate, identifying an average of 15 percent of the responses by arrestees who lied (based on the urine test) about recent drug use for all five drugs. LVA correctly identified 21 percent of the deceptive responses as deceptive; CVSA® identified 8 percent.
The specificity rates—the percentage of nondeceptive respondents who, based on their urine tests, were correctly classified as nondeceptive—were much higher, with an average of 91.5-percent accuracy for the five drugs. Again, LVA performed better, correctly identifying 95 percent of the nondeceptive respondents; CVSA® correctly identified 90 percent of the nondeceptive respondents.
We then used a plotting algorithm, comparing the sensitivity and specificity rates, to calculate each VSA program's overall "accuracy rate" in detecting deception about drug use.[10] We found that the average accuracy rate for all five drugs was approximately 50 percent.
Does VSA Deter People From Lying?
Although the two VSA programs we tested had about a 50-percent accuracy rate in determining deception about recent drug use, might their very presence during an interrogation compel a person to be more truthful?
This phenomenon—that people will answer more honestly if they believe that their responses can be tested for accuracy—is called the "bogus pipeline" effect.[11] Previous research has established that it is often present in studies that examine substance use.][12
To determine whether a bogus pipeline effect existed in our study, we compared the percentage of deceptive answers to data from the Oklahoma City Arrestee Drug Abuse Monitoring (ADAM) study (1998–2004), which was conducted by the same VSA researchers in the same jail using the same protocols. The only differences—apart from the different groups of arrestees—were that the ADAM survey was longer (a 20-minute survey compared with the VSA study's 5-minute survey) and did not involve the use of VSA technology.
In both studies, arrestees were told that they would be asked to submit a urine sample after answering questions about their recent drug use. In the VSA study, arrestees were told that a computer program was being used that would detect deceptive answers.
Arrestees in the VSA study were much less deceptive than ADAM arrestees, based on responses and results of the urine test (that is, not considering the VSA data). Only 14 percent of the VSA study arrestees were deceptive about recent drug use compared to 40 percent of the ADAM arrestees. This suggests that the arrestees in the VSA study who thought their interviewers were using a form of "lie detection" (i.e., the VSA technology) were much less likely to be deceptive when reporting recent drug use.

The Bottom Line: To Use or Not Use VSA
It is important to look at both "hard" and "hidden" costs when deciding whether to purchase or maintain a VSA program. The monetary costs are substantial: it can cost up to $20,000 to purchase LVA. The average cost of CVSA® training and equipment is $11,500. Calculating the current investment nationwide—more than 1,400 police departments currently use CVSA®, according to the manufacturer—the total cost is more than $16 million not including the manpower expense to use it.
The hidden costs are, of course, more difficult to quantify. As VSA programs come under greater scrutiny—due, in part, to reports of false confessions during investigations that used VSA—the overall value of the technology continues to be questioned.[13]
Therefore, it is not a simple task to answer the question: Does VSA work? As our findings revealed, the two VSA programs that we tested had approximately a 50-percent accuracy rate in detecting deception about drug use in a field (i.e., jail) environment; however, the mere presence of a VSA program during an interrogation may deter a respondent from answering falsely. Clearly, law enforcement administrators and policymakers should weigh all the factors when deciding to purchase or use VSA technology.
NIJ Journal No. 259, March 2008
NCJ 221502
About the Author
Kelly Damphousse is associate dean of the College of Arts and Sciences and Presidential Professor of Sociology at the University of Oklahoma. He has 20 years of criminal justice and drug research experience. From 1998 to 2004, Damphousse served as the site director of the Arrestee Drug Abuse Monitoring program in Oklahoma City and Tulsa, Oklahoma. He has directed several statewide and nationwide program evaluation projects.”

On 10 February 2004 the Washington University in St Louis published the following article written by Gerry Everding:

“Research casts doubt on voice-stress lie detection technology
By Gerry Everding February 10, 2004January 13, 2016

Voice-stress analysis, an alternative to the polygraph as a method for lie detection, is already widely used in police and insurance fraud investigations. Now, however, it is being touted as a powerful and effective tool for an array of new applications — everything from the screening of potential terrorists in the nation’s airports to catching wayward spouses in messy marital disputes.
Despite its booming popularity, a number of federally sponsored studies have found little or no scientific evidence to support the notion that existing voice-stress technologies are capable of consistently detecting lies and deceptions.
The Truster hand-held “Emotion Reader” is one of many commercial products that claim to detect lies and deception using voice-stress analysis.

“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.
In one scenario, for example, participants were questioned about a mock crime that they had witnessed but voice analysis correctly identified deception in only about 24 percent of individuals who were being deceptive. It also incorrectly identified deception among 18 percent of non-deceivers. In another experiment, Sommers induced high levels of stress by having participants play a video game that got increasingly difficult. Although none of the participants in this study were deceptive, Vericator still indicated that about 20 percent of the individuals were lying.
“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.”
In theory, voice-stress analysis works by measuring slight inaudible fluctuations in the human voice known as “micro-tremors.” Voice-stress analysis systems, which generally include a microphone, tape recorder and related 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 an attempt to lie or deceive. Voice patterns are analyzed, graphed and displayed on a computer screen.
Various distributors of voice-stress analysis systems suggest that recent advances in the technology, such as layered voice-stress analysis, have elevated voice-stress lie detection to new levels of dependability and effectiveness. Some suggest that the dismal performance of voice-stress analysis lie detection in recent federal studies can be attributed to improper test conditions or to tests being conducted using outdated and inferior versions of the technology. Still, while many governmental investigative, military and law enforcement agencies have expressed an eagerness to find a credible new means of lie detection, study after study has failed to yield strong scientific evidence in support of the technology.


Other reports, research on validity of voice-stress analysis lie detection:
“A review of the literature revealed that there have been no scientific studies conducted, to date, to measure the validity of the computer stress analyzed to detect deception,” concluded a November 2003 study by the Virginia Department of Professional and Occupational Regulation. “It has been argued that the computer stress analyzer is more cost effective, convenient, and more user friendly than the traditional polygraph equipment, however, one question still remains unanswered: how reliable is the equipment in its actual ability to detect, measure, and display changes in voice frequency? Has it ever been scientifically measured? The answer to this question is ‘no.'”
Similar conclusions were reached in “Voice Stress Devices and the Detection of Lies,” an overview of current voice-stress technologies written by Donald J. Krapohl, Andrew H. Ryan and Kendall W. Shull; and published in Policy Review, the official publication of the International Chiefs of Police National Law Enforcement Policy Center.
The American Polygraph Association offers an online overview on understanding “Truth v. Myth” when it comes to comparing voice stress and polygraph technologies.

POLYGRAPH
The American Polygraph Association is the International body regulating Polygraph testing worldwide.
This body is constantly striving to ensure the best possible polygraph testing are being done by facilitating research and development in the Polygraph field.
The following is published on their website regarding the validity of the polygraph:

“Polygraph Validity Research
The American Polygraph Association (APA) believes that scientific evidence supports the validity of polygraph examinations that are conducted and interpreted in compliance with documented and validated procedure. Thus, such examinations have great probative value and utility for a range of uses, including criminal investigations, offender management, and selection of applicants for positions requiring public trust.  The APA Standards of Practice set some of the highest professional requirements for its members to ensure their polygraph services are valuable, reliable, and promote ethically responsible practices.  The APA also produces a variety of model policies that represent the current understanding of best practices, and makes them widely available so that polygraph examiners (both APA members and non-members) and their clients can be aware of what constitutes a valid examination process.  The APA believes that well informed departments, agencies, and clients will insist on APA members for their polygraph services.

Recently the APA undertook an exhaustive review of all of the peer-reviewed publications on polygraph testing that represented field practices and which met the requirements of the APA Standards of Practice.  A meta-analysis was conducted, and a report was completed in late 2011.  An executive summary of the report is freely available to the public through this website. Please visit  the Meta-Analytic Survey of Criterion Accuracy of Validated Polygraph Techniques page to download the report and FAQ page

The executive summary reports that 38 studies satisfied the qualitative and quantitative requirements for inclusion in the meta-analysis. These studies involved 32 different samples, and described the results of 45 different experiments and surveys. They included 295 scorers who provided 11,737 scored results of 3,723 examinations, including 6,109 scores of 2,015 confirmed deceptive examinations, 5,628 scores of 1,708 confirmed truthful exams. Some of the cases were scored by multiple scorers and using multiple scoring methods.   The data showed that techniques intended for event-specific (single issue) diagnostic testing produced an aggregated decision accuracy of 89% (confidence interval of 83% - 95%), with an estimated inconclusive rate of 11%.  Polygraph techniques in which multiple issues were encompassed by the relevant questions produced an aggregated decision accuracy of 85% (confidence interval 77% - 93%) with an inconclusive rate of 13%. The combination of all validated PDD techniques, excluding outlier results, produced a decision accuracy of 87% (confidence interval 80% - 94%) with an inconclusive rate of 13%. These findings were consistent with those of the National Research Council’s (2003) conclusions regarding polygraph accuracy, and provide additional support for the validity of polygraph testing when conducted in accordance with APA Standards of Practice. “

Conclusion

We at Polygraph Proactive want to state categorically that we distance ourselves totally from any form of Voice Stress Analyses processes.
From the above publications and research, we conclude that Voice Stress Analyses is most probably an unscientific and unreliable process, to say the least.
As such, we are of the opinion that it would be unethical for us to subject individuals to such a process, being is possession of the above information.
We take our Polygraph work very seriously as we are well aware that we are dealing with human lives. As such, we cannot be part of a process where an individual’s future it determined by a process to be found “not being better than flipping a coin”.
All our examiners are fully trained and qualified Forensic Psychophysiologists, trained by the American International Institute of Polygraph, Atlanta, Georgia, USA, which is an accredited Training facility, accredited by the American Polygraph Association.
We are further only using Techniques which are validated and approved by the American Polygraph Association.