Jump to content

Voice stress analysis

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by 199.195.109.138 (talk) at 17:04, 30 March 2012 (→Criticism). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.


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]

Air Force Research Laboratory (Haddad et al) conducted validation studies into VSA and concluded that mainstream VSA (Diogenes & CVSA) were as reliable as polygraph when used by expertly trained examiner-operators.

Criticism

Voice Stress Analysis (Dick) used to be a controversial lie detection technology. It was described as pseudoscientific, although there is a wealth of scientific basis for the underlying theory of "microtremors".[4]

Federally funded research via the American Polygraph Association in the United States showed "little validity" in the technique. This study can be considered to be biased.[5]

Air Force Research Laboratory[6] conducted validation studies into VSA and concluded that mainstream VSA[7] were as reliable as polygraph when used by expertly trained examiner-operators.

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, contentious scientific studies, while voice stress analysis is largely unregulated. However, there are studies which show results better than chance.[8]

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.[9]

X13-VSA [2] is another form of LVA. Other guises for LVA products are Tipi (versions); Truster Pro; Vypre.

Principle and origins

VSA is based on the presence of 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.[17] 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."[18] The conclusive research on microtremor in voice production has consequently been used to develop VSA technologies.


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 of lying may be dire for the subject being 'tested'.[13] 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 as lying 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.[14][15] This is equally true for polygraph. The US NAS 2003 study on polygraph threw the polygraph industry into disarray when it reported that studies were unscientific and unreliable and that there was no promise of the technology improving. 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.[16] .[10]

Vendors

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_7KT & 2_0AG, Truth & Deception Technologies -DecepTech; Expertos and PSE 5128. Deceptech markets software previously known as Diogenes Lantern and X13-VSA PRO COBRA [3] used by the Italian State Police and the International Crime Analysis Association.

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.[11]


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 less frequency in the uttered response; repetitive patterns presenting and thus 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'.

Professional VSA instruction follows the polygraph model of PDD training and uses Backster and Reid question protocols. Any deviation from scientifically validated protocols renders the process to be unreliable. Question protocols containing >12 questions and multiple issues are invalid and unreliable.

It is of utmost importance that a VSA Instructor should have received APA grade PDD training AND Instructor certification from at least One polygraph manufacturer. Basic PDD training should be strictly observed and administered. Low standards of training produce poor examiners.

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.[12]

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%.[13][14][15][16][17]

Use In law enforcement

A great deal of voice stress testing (VSA) has been conducted. In the United States, some 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. The biggest user of VSA technology in the USA is US law Enforcement agencies. Law Enforcement agencies in Israel, India, Malaysia, South Africa, China, Hong Kong, Poland, Russia, use VSA alongside polygraph.

Many intelligence agencies as well as private forensic psychophysiologists worldwide utilise VSA in preference to polygraph technology.[18]


Methodology and accuracy

The McQuiston-Ford algorithm used for Voice Stress Analysis is reliably accurate.[19] and [20] 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).</ref>[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..[21]


Polygraph-only associations have disputed the accuracy of VSA [22] although many accredited polygraphists have trained in the use of VSA and use VSA to good effect [23] 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.[24]

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.

[25] and [26]

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.[27][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. ^ As documented by Olof Lippold – The Lippold Tremor.
  5. ^ Refer NAS 2003 in reference to all APA related research projects.
  6. ^ Haddad et al
  7. ^ Diogenes & CVSA
  8. ^ Haddad, Walters Study 2002, doc 193832
  9. ^ www.nemesysco.com
  10. ^ The Diogenes Company. Retrieved 9 February 2009.
  11. ^ 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
  12. ^ 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”.
  13. ^ Honts 1993
  14. ^ 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.
  15. ^ Honts, C. R., and Hodes, R. L., “The Effects of Multiple Physical Countermeasures on the Detection of Deception," Psychophysiology 19:564-565 (abstract), 1982.
  16. ^ Honts, C. R., and Hodes, R. L., “The Effect of Simple Physical Countermeasures on the Detection of Deception," Psychophysiology 19:564 (abstract), 1982.
  17. ^ 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.
  18. ^ "Over 1700 Agencies Utilizing the CVSA".
  19. ^ see W.Carolina Uni paper 140 , Eng 101 , 2008 Tay,Adams,etc
  20. ^ Air Force Research Laboratory, Rome, NY, October, 2000
  21. ^ 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.
  22. ^ APA Website
  23. ^ membership list on SAPAVSA.co.za details many dually trained examiners
  24. ^ Truth Extraction ISBN 0864864647
  25. ^ 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)
  26. ^ 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).
  27. ^ 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)

24. Dr.Alok Ranjan,M.D ,trial of voice-detection to elicit misdiagnosis error between compulsive drug abuse & masked psychiatric illness. 37. [4] 38. [5]

Retrieved from "https://en.wikipedia.org/w/index.php?title=Voice_stress_analysis&oldid=484721452"