Voice stress analysis

Voice Stress Analysis (VSA) technology is said to record psychophysiological stress responses that are present in human voice, when a person suffers psychological stress in response to a stimulus (question) and where the consequences may be dire for the subject being 'tested'.^[1]

In the Detection Of Deception (DOD) scenario, the voice-stress produced in response to a Relevant Question ("did you do it?") is referred to as psychological stress or 'deceptive stress'. No DOD technology can detect a lie or truth unequivocally. It is the fear of being exposed to the question being posed that produces the 'high stress' voice signature, aka voice graph or voice tracing.

The technique's accuracy remains debated. There are independent research studies that support the use of VSA as a reliable lie detection technology, whilst there are other studies that dispute its reliability.^[2][3]

Criticism

Voice stress analysis has been described as pseudoscientific,^[4] and there is no known scientific basis for the underlying theory of "microtremors". Federally funded research in the United States showed "little validity" in the technique.^[5] A study by Virginia State in 2003, at which time the technique was in widespread use, concluded that "Because there have been no independent scientific studies conducted on the reliability of the computer voice analyzer to detect deception, the Board recommends to the Director of the Department of Professional and Occupational Regulation that computer voice analyzer equipment should not be approved in Virginia at this time.",^[6] though a number of academic studies are available which call into question the validity of the technique^{[7][8][9][10][11][12][13][14]}

There is tension between the voice stress analysis community and the polygraph community, due in the main to the fact that the polygraph is heavily regulated and has been subject to numerous detailed scientific studies, while voice stress analysis is largely unregulated and there are few studies (other than by manufacturers and proponents) which show results better than chance^{[citation needed]}.

VSA vs LVA

VSA is distinct from Layered Voice Analysis (LVA). LVA is used to measure many different components of the voice, but is not reliable in the detection of 'deceptive stress'. LVA measures a wide range of emotions, including excitement, confusion, attention and more. LVA is available in many different forms of products, ranging from server based intelligence use systems, to hand-held devices and standard PC software.

The main difference in the method of operation between LVA and VSA is based on the analyzed frequencies ranges: while VSA focuses on the 8–14 Hz range (which is picked up by specialised microphones), LVA uses a wider spectrum range to extract information that is amusing but not particularly relevant to DOD.^[15]

Principle and origins

VSA is based on hypothesis that there are infrasonic components of human voice not audible to observers caused by a physiological phenomenon present in muscles called "microtremor". It was discovered in 1957 by British physiologist Olaf Lippold.^[16] Further investigation by other researchers explored the possibility of the presence of microtremor in the muscles controlling the voicebox. The experiment was made by attaching electrodes to the cricothyroid muscle and the posterior cricoarytenoid muscle and measuring EMG signals. Detecting microtremor during sustained speech was not deemed possible because the EMG activity changed too rapidly. The experiment was therefore limited to measuring the presence of microtremor in the frequency range of 1 through 20 Hz in sustained vowel phonation, but yielded no positive results. It was concluded that "the electrical energy was randomly distributed throughout the spectrum."^[17] The inconclusive research on microtremor in voice production has consequently been used to claim that the phenomenon can be used for creating technology capable of lie detection by detecting microtremor in recorded speech.^[18]

The original VSA technology was devised by three former US Army personnel. The three, Bell, McQuiston & Ford, developed the PSE 1, an analogue machine. The same three, working under Dektor Counterintelligence and Security Inc., manufactured the PSE 1000 and later the PSE 2000.

The National Institute Of Truth Verification (NITV, West Palm Beach) then produced and marketed an analogue instrument based on the PSE & digitized it in April 1997, based on the McQuiston-Ford algorithm. In the past 10 years VSA has been used primarily in digital applications: Digital Voice Stress Analysis (D-VSA). The primary suppliers worldwide are: NITV(USA)-CVSA; POLYVSA(TVT Centre RSA)- AVSA PRO 1,8. Older manual systems are supplied by TDT (previously known as Diogenes Lantern); Expertos and PSE 5128.

The primary use of VSA is in the arena of "Detection Of Deception". As with the polygraph, VSA technology is inert. It has no artificial intelligence component. It is the use of the recorded data as a means for lie detection that remains controversial.^[19]

Another interesting application used by the Italian State Police, the International Crime Analysis Association and other law enforcement agencies worldwide, law firms, journalists and professional investigators is the X13-VSA Voice Stress Analyzer http://www.lie-detection.com

Applications

The purpose of a VSA examination is to determine the truthfulness of responses made by an examinee regarding the subject under investigation. Determinations are made by analyzing and scoring the voice-grams produced by the examinee. Traditional analysis of voice grams was achieved by allocating "percentages of stress" ( % ) according to the patterns so produced^{[citation needed]}.

High levels of (deceptive) stress indicate that the examinee is deceptive as is the case with polygraph. In respect of VSA, squared voice grams indicates higher stress, whilst 'wave form' or 'domed' signatures indicate less stress.

Questions may be posed to elicit simple "yes" or "no" answers, but can be posed to produce a narrative response. Questions are formulated for each individual being examined to compare situational stress signatures with Control Question and Relevant Question signatures, in order to identify (deceptive) 'stress signatures'.

VSA technology together with validated testing protocols, is designed to protect the innocent and avoid 'false positive' results. VSA is designed to assist any investigation by establishing the veracity of a subject's verbal responses.^[20]

Devices used to analyze voice stress are usually used in the presence of the individual under investigation; however, they can also be used without his or her knowledge. Since all that is needed is a voice, a wireless microphone or a tape recording can provide the necessary input signal.

There are no known physical countermeasures for VSA. Conversely according to Honts et al., the simple use of a 'tack' placed under the tongue of the examinee, to be used as a countermeasure, can reduce the accuracy of polygraph results from 98% to 26%.^{[21][22][23][24][25]}

Use In law enforcement

A great deal of voice stress testing (VSA) has been conducted. In the United States, most states do not regulate the private use of these devices. However, the CIA and FBI both use VSA at times, in their own investigations. The technology is currently recognized in 43 states.

Many intelligence agencies as well as private forensic psychophysiologists worldwide utilise VSA in preference to polygraph technology.^[26]

.

Methodology and accuracy

The McQuiston-Ford algorithm used for Voice Stress Analysis is reliably accurate.^{[27][verification needed]} The recorded "micro tremors" in a persons voice are converted via the algorithm into a scorable voice gram. The discrepancy in researched accuracy may result from incorrectly trained or non-trained persons utilizing the technology incorrectly. This is evident by some Polygraphists trying to "test" VSA technology without having received accredited training in the use thereof also by applying Poly Protocols to VSA & vice versa which cannot work.^[28]

Polygraph-only associations have disputed the accuracy of VSA^{[citation needed]}, although many accredited polygraphists have trained in the use of VSA and use VSA to good effect^{[citation needed]}. The traditional analysis and scoring of voice-grams by means of assigning 'percentages' is time consuming.

In 2002, Clifton Coetzee (Polygraph & VSA Instructor) devised a scoring method for voice grams incorporating the 'UTAH 7 Point' scoring system, as used by modern day polygraphists. Reactive or Responsive patterns are assigned a weighting of +3 to -3.^{[citation needed]}

The use of CQT testing protocols developed by John Reid and Cleve Backster are used for greater reliability of VSA results. It is important that VSA examiners be skilled in the use of enforced, timed pauses between stimulus (question) and response (answer). As in the polygraph situation, the fight or flight response has onset and conclusion delays, which must be considered by examiners to achieve reliable results.

In 2010 through to 2011, Clifton Coetzee and Jean-Louis Gouin (Alpes-Software: Developer of original Diogenes Lantern, which is now re-labelled as TDT )developed AVSA PRO, which is a unique, evolutionary, fully automatic VSA system. AVSA PRO is programmed to cater for cadence control being consistent in every question posed. Examiner induced errors have been eliminated. AVSA PRO is based on a neural network - another major innovation in the worldwide vsa industry. Scoring of automatically captured and numerically identified voice wavs is according to the neural network database, developed from Expert blind scoring of 000's of voice wavs, with the input of known outcomes.

^[29][30]

The American Polygraph Association's website lists conclusions from multiple studies, intended by the polygraph industry to discredit vsa, into the accuracy of voice stress analysis as a means of detecting the subject's truthfulness. Some researchers or polygraph professionals^{[citation needed]} cast doubt on the validity of the results of such tests; many describe the results as no better than chance.^{[31][verification needed]}

The National Academy of Sciences (USA) severely criticized the validity of APA studies into polygraph as "biased, unscientific and industry funded." The NAS study concluded that there has been no scientific advancement in polygraphy. Further, that polygraphy was unreliable as a lie detection technology. ( http://www.nap.edu/openbook.php?isbn=0309084369 )

References

1. ^ Ruiz, Selye, & Guell, 1990. Voice analysis to predict the psychological or physical state of a speaker. Published in Aviation, Space, and Environmental Medicine, 1990. Ruiz et al. reports that their “research suggests that psychological stress may be detected as acoustic modifications in the fundamental frequency of a speakers voice” and “that the fundamental frequency of the vocal signal is slowly modulated (8-14 Hz) during speech in an emotionally neutral situation. In situations demanding increased ‘mental or psychomotor’ activity, the 8-14 Hz modulation then decreases as the striated muscles surrounding the vocal cords contract in response to the arousal, thus limiting the natural trembling”
2. ^ Mitchell S. Sommers, an associate professor of psychology in Arts & Sciences at Washington University in St. Louis's Results. [1]
3. ^ Horvath, F. "Detecting deception: the promise and the reality of voice stress analysis." Journal of Forensic Science. 1982 Apr;27(2):340-51. PMID 7047675
4. ^ Tavris & Aronson, Mistakes were made, Ch. 5
5. ^ Assessing the Validity of Voice Stress Analysis Tools in a Jail Setting, Kelly R. Damphousse ; Laura Pointon ; Deidra Upchurch ; Rebecca K. Moore
6. ^ STUDY OF THE UTILITY AND VALIDITY OF VOICE STRESS ANALYZERS, Virginia for Professional and Occupational Regulation, 2003
7. ^ Brenner, M., Branscomb, H., & Schwartz, G. E. (1979). Psychological stress evaluator: Two tests of a vocal measure. Psychophysiology, 16(4), 351-357: "Validity of the analysis for practical lie detection is questionable"
8. ^ Cestaro, V.L. (1995). A Comparison Between Decision Accuracy Rates Obtained Using the Polygraph Instrument and the Computer Voice Stress Analyzer (CVSA) in the Absence of Jeopardy. (DoDPI95-R-0002). Fort McClellan, AL: Department of Defense Polygraph Institute. "Accuracy was not significantly greater than chance for the CVSA."
9. ^ DoDPI Research Division Staff, Meyerhoff, J.L., Saviolakis, G.A., Koenig M.L., & Yourick, D.L. (In press). Physiological and Biochemical Measures of Stress Compared to Voice Stress Analysis Using the Computer Voice Stress Analyzer (CVSA). (DoDPI01-R-0001). Department of Defense Polygraph Institute. "Direct test of the CVSA against medical markers for stress (blood pressure, plasma ACTH, salivary cortisol) found that CVSA examiners could not detect known stress. This project was a collaborative effort with Walter Reed Army Institute of Research."
10. ^ Fuller, B.F. (1984). Reliability and validity of an interval measure of vocal stress. Psychological Medicine, 14(1), 159-166: "Validity of voice stress measures was poor."
11. ^ Janniro, M. J., & Cestaro, V. L. (1996). Effectiveness of Detection of Deception Examinations Using the Computer Voice Stress Analyzer. (DoDPI95-P-0016). Fort McClellan, AL : Department of Defense Polygraph Institute. DTIC AD Number A318986. "Chance-level detection of deception using the CVSA as a voice stress device."
12. ^ Hollien, H., Geison, L., & Hicks, J. W., Jr. (1987). Voice stress analysis and lie detection. Journal of Forensic Sciences, 32(2), 405-418. "Chance-level detection of stress. Chance-level detection of lies."
13. ^ Suzuki, A., Watanabe, S., Takeno, Y., Kosugi, T., & Kasuya, T. (1973). Possibility of detecting deception by voice analysis. Reports of the National Research Institute of Police Science, 26(1, February), 62-66. Conclusion: Voice measures were not reliable or useful.
14. ^ Waln, R. F., & Downey, R. G. (1987). Voice stress analysis: Use of telephone recordings. Journal of Business and Psychology , 1(4), 379-389. "Voice stress methodology did not show sufficient reliability to warrant its use as a selection procedure for employment."
15. ^ www.nemesysco.com
16. ^ Lippold, O., Redfearn, J., Vuco, R. "he Rhythmical Activity Of Groups Of Muscle Units In The Voluntary Contraction Of Muscle" in The Journal Of Physiology, 137 (1957).
17. ^ Shipp, T. & Izdebski, K. "Current Evidence for the Existence of Laryngeal Macrotremor and Microtremor." in Journal of the Acoustical Society of America 48 (1981)
18. ^ The Diogenes Company. Retrieved 9 February 2009.
19. ^ Chapman, J. Criminal Justice Department, Corning Community College, NY. "The Psychological Stress Evaluator As A Tool For Eliciting Confessions", 1989. Chapman selected 211 criminal cases at random from 2,109 known-conclusion cases where voice stress analysis was used to test suspects. Professor Chapman’s study confirmed that voice stress analysis was accurate when utilized as a truth verification device and produced a confession rate of 94.8% of the cases where deception was indicated
20. ^ Heisse, J. “Is The Micro-Tremor Usable? - The Micro-Muscle Tremor In The Voice.” U.S. House Subcommittee of the Committee on Government Operations, 1974. Heisse analyzed 91 known-conclusion criminal cases utilizing voice stress analysis and determined that “Audio stress analysis seems to be valid in detecting changes in various psycho physiological parameters so that a trained examiner utilizing standardized techniques can evaluate these changes and thus utilize the instrument in truth and deception”.
21. ^ Honts 1993
22. ^ Honts, C. R., and Hodes, R. L., “The Effect of Simple Physical Countermeasures on the Detection of Deception," paper presented at meetings of the Society for Psychophysiological Research, Minneapolis, Minn., 1982.
23. ^ Honts, C. R., and Hodes, R. L., “The Effects of Multiple Physical Countermeasures on the Detection of Deception," Psychophysiology 19:564-565 (abstract), 1982.
24. ^ Honts, C. R., and Hodes, R. L., “The Effect of Simple Physical Countermeasures on the Detection of Deception," Psychophysiology 19:564 (abstract), 1982.
25. ^ Honts, C. R., Raskin, D. C., and Kircher, J. C., “Detection of Deception: Effectiveness of Physical Countermeasures Under High Motivation Conditions, " 1 paper presented at meetings of the Society for Psychophysiological Research, September 1983.
26. ^ "Over 1700 Agencies Utilizing the CVSA". http://www.nitv1.com/Agenciesusing.htm. 
27. ^ see W.Carolina Uni paper 140 , Eng 101 , 2008 Tay,Adams,etc this & Bell - Mcquiston DO NOT capture Total pattern .Air Force Research Laboratory, Rome, NY, October, 2000. Funded by the National Institute of Justice, a three-year study by the AFRL determined that voice stress analysis achieved an accuracy rate of 100% when used to detect stress in 45 known-conclusion responses. (Available from http://extraafrl.af.mil/news/fa1100/features/detects:stress:feature.pdf).
28. ^ Chapman, J. Criminal Justice Department, Corning Community College, NY. “The Psychological Stress Evaluator As A Tool For Eliciting Confessions”, 1989. Chapman selected 211 criminal responses at random from 2,109 known-conclusion responses where voice stress analysis was used to test suspects. Professor Chapman’s study confirmed that voice stress analysis was accurate when utilized as a truth verification device and produced a confession rate of 94.8% of the responses where deception was indicated.
29. ^ Lippold, O. “Oscillations In The Stretch Reflex Arc And The Origin Of The Rhythmical 8-12 C/S Component Of The Physiological Tremor.” The Journal Of Physiology, February, 1970. Lippold first discovers the physiological tremor in the human voice in the 8-12 Hz range (Available from Library of Congress)
30. ^ Lippold, O., Redfearn, J., Vuco, R. “The Rhythmical Activity Of Groups Of Muscle Units In The Voluntary Contraction Of Muscle.” The Journal Of Physiology, August, 1957. Lippold, Redfearn and Vuco begin exploring the correlation between muscle activity and stress (Available from Library of Congress).
31. ^ Cestaro, V. Department of Defense Polygraph Institute, Ft. McClellan, AL. “A Comparison Between Decision Accuracy Rates Obtained Using the Polygraph Instrument and the Computer Voice Stress Analyzer in the Absence of Jeopardy”, August, 1995. Cestaro reports that “the lab simulations established that the CVSA performs electrically according to the manufacturer’s theory of operation” and, even in the absence of jeopardy, which is a basic requirement in detection of deception, “These data indicate that there may be a systematic and predictable relationship between voice patterns and stress related to deception” (Available from DoD web site: http://www.dodpi.army.mil/research/research.htm)

37. [2]