Voice stress analysis

From Wikipedia, the free encyclopedia
Jump to: navigation, search

Voice stress analysis (VSA) technology is said to record psychophysiological stress responses that are present in the human voice when a person suffers psychological stress in response to a stimulus (e.g., a question), and the consequences of the person's answer may be dire.[1] This is based on the belief that non-verbal content of the voice carries, among other things, information about the physiological and psychological state of the speaker.[2]

Support and criticism[edit]

The use of Voice Stress Analysis (VSA) technology to detect deception is highly controversial, and has been classified as Pseudoscience by academics[3] Discussions about its application revolve around whether this technology can indeed reliably detect stress, and if so, whether deception can be inferred from this stress. The latter is a logical inference problem referred to as the Othello error. Several studies published in peer reviewed journals showed VSA to perform at chance level when it comes to detecting dception. Horvath, McCloughan, Weatherman, and Slowik, (2013),[4] for example, tested VSA on the recordings of interrogation of 74 suspects. Eighteen of these suspects later confessed, making the deception the most likely ground truth. With 48% accurate classification, VSA performed at chance level. Several other studies showed similar results (Damphousse, 2008; Harnsberger, Hollien, Martin, & Hollien, 2009).[5][6] In 2003, the National Research Council concluded “Overall, this research and the few controlled tests conducted over the past decade offer little or no scientific basis for the use of the computer voice stress analyser or similar voice measurement instruments”.[7]

A new Indian open access Journal (the International Journal of Electrical, Electronics and Computer Engineering (IJEECE)) published a study claiming that Voice Stress Analysis (VSA) technology can identify emotional stress better than polygraph.[8] This study did not, however, make any experimental comparison between VSA and the polygraph, meaning that the evidence for this claims remain mysterious.

An Ukrainian Journal issued by Kyiv Scientific Research Institute of Court Expertise, published an 18-year study evaluating the use of the voice stress analysis technology for the detection of stress associated with possible deception. Using a combinatorial approach of VSA and a standardized questioning process, the author was able to show that VSA detected stress associated with criminal activities in 95% of the confession obtained cases studied. Chapman found no cases wherein a confession was obtained in the absence of stress. In particular, the most considerable stress levels were detected during the investigation of murder, grand larceny and sexual crimes. Chapman identified that when VSA is utilized as an investigative decision support tool in accordance with required operating procedures, and standard VSA interviewing techniques are employed, elicited confessions from criminal suspects can strongly be predicted based upon results of their VSA examinations. Further, VSA can be used by trained professionals to support the acquisition of court admissible criminal confessions at a rate superior to other legal interrogation methods currently employed by the criminal justice system.[9] Such a study, however, suffers from sampling bias. Suspects will only be interrogated when they fail the test. Consequently, confessions will only follow in those cases where the test outcome was deception indicated. When one then rounds up all the cases in which a confession was obtained, it should come as no surprise that the confessions match deception indicated test outcomes to a high degree. This would happen even when a test performs at chance level.[10]

Proceedings of the 2005 Hawaii International Conference on System Sciences, identified that VSA technology correctly classified 73% of deceptive examinees. Yet, for truth tellers - with 52% accurate classification - it performed as well as a coin flip.[11]

In a three year study conducted by the U.S. Air Force Research Laboratory in Rome New York, on voice stress analysis, it was determined that the voice stress units tested were able to recognize stress in the spoken voice. Additionally, these units performed equally whether the voice was a live test or a recorded one. The study also provided the caveat that caution should be taken when using voice stress analysis in that it should only be used as an investigative tool and not relied on for a case conclusion.[12]

Voice stress units[edit]

The International Association of Voice Stress Analysts, Inc. (IAVSA), is the recognized authority in the United States for voice stress analysis and its application. The IAVSA currently recognizes three units, the VIPRE Voice Stress Analyzer, the Computer Voice Stress Analyzer (CVSA), and the Forensic Voice Stress Analyzer (FVSA).[13] Although not recognized by the IAVSA, Nemesysco [14] also claims to be able to measure psychological state and consequently deception form the voice.

Principle and origins[edit]

In 1970, and prior to the publishing of Lippold's article in 1971, three military officers retired from the U.S. Army and formed a company they named Dektor Counterintelligence and Security (CIS). The three officers were Alan Bell, Bill Ford and Charles McQuiston. Bell's expertise was in counterintelligence, Ford's was in electronics, and McQuiston's was in polygraphy. Ford had invented an electronic device that utilized the theory of Lippold, Halliday and Redfearn in which he tape-recorded the human voice, slowed it down to one-third or one-fourth its normal rate, and fed it through several low pass filters which then fed the signal into an EKG strip chart recorder. The strip chart recorder then made chart tracings on heat-sensitive paper. They named their device the Psychological Stress Evaluator (PSE). According to Allan Bell Enterprises, "All lie-detection examinations or evaluations are predicated upon the fact that telling a significant lie will produce some degree of psychological stress. Psychological stress, in turn, causes a number of physiological changes."[15]

Methodology and accuracy[edit]

The recorded "micro tremors" in a person's 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.[speculation?] This is evident by some Polygraphists trying to "test" VSA technology without having received accredited training in the use thereof.[16][verification needed]

The American Polygraph Association's Web site lists conclusions from multiple studies, into the accuracy of voice stress analysis as a means of detecting the subject's truthfulness. Some researchers or polygraph professionals cast doubt on the validity of the results of such tests; many describe the results as no better than chance.[17]

The National Academy of Sciences published a 2003 study on the polygraph, in which they concluded that the evidence of its efficacy is "scientifically weak".[18] According to the American Psychological Association, "most psychologists agree that there is little evidence that polygraph tests can accurately detect lies".[19] A similar critique has been voiced against VSA.

Notable examples of use[edit]

Following the 2012 case in which George Zimmerman fatally shot Florida teenager Trayvon Martin, Zimmerman was given a voice stress analysis test by the police department of Sanford, Florida. He passed the test.[20] A videotape of the test was publicly released in June 2012.[21]

Federal judge approves computer voice stress analysis to monitor sex offenders. A recent ruling from a U.S. Federal court judge may require sex offenders to submit Computer Voice Stress Analyzer (CVSA) examinations throughout the post-release supervision process.[22]

Confession made following a voice stress examination was allowed to be used as evidence in a rape trial.[23]


  1. ^ Ruiz, Selye, & Guell, 1990. "Voice analysis to predict the psychological or physical state of a speaker", Aviation, Space, and Environmental Medicine, 1990. Ruiz et al. report 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. ^ Rothkrantz, L. J., Wiggers, P., Wees, J. A., & Vark, R. J. (2004). Voice Stress Analysis. Text, Speech and Dialogue Lecture Notes in Computer Science, 449-456. doi:10.1007/978-3-540-30120-2_57
  3. ^ Eriksson, A., & Lacerda, F. (2007). Charlatanry in forensic speech science: A problem to be taken seriously. International Journal of Speech, Language and the Law, 14(2), 169-193.
  4. ^ Horvath, F., McCloughan, J., Weatherman, D., & Slowik, S. (2013). The Accuracy of Deception During Police Questioning. Journal of forensic sciences, 58, 385-392.
  5. ^ Damphousse, K. R. (2008). Voice stress analysis: Only 15 percent of lies about drug use detected in field test. NIJ Journal, 259, 8-12.
  6. ^ Harnsberger, J. D., Hollien, H., Martin, C. A., & Hollien, K. A. (2009). Stress and Deception in Speech: Evaluating Layered Voice Analysis. Journal of forensic sciences, 54, 642-650.
  7. ^ National Research Council (2003). The Polygraph and Lie Detection. Committee to review the scientific evidence on the polygraph. Division of Behavioral and Social Sciences and Education. Washington, DC: The National Academic Press.
  8. ^ Patil, V. P., Nayak, K. K., & Saxena, M. "Voice Stress Detection", 2, 148-154. Journal of Electrical, Electronics and Computer Engineering, IJEECE (online) ISSN 1748-8893.
  9. ^ Chapman, J. (2012). "Field Evaluation of Effectiveness of VSA (Voice Stress Analysis) Technology in a US Criminal Justice Setting". Scientific Journal Criminalistics and Court Expertise, Number 57 (2012 Annual Issue), 238-250.
  10. ^ Iacono, W. G. (1991). Can we determine the accuracy of polygraph tests? In P. K. Ackles, J. R. Jennings, & M. G. H. Coles (Eds.), Advances in psychophysiology (pp. 201–201). Greenwich, CT: JAI Press
  11. ^ Sprague, R. H. (2005). "Evaluation of Voice Stress Analysis Technology". HICSS 2005 38th Hawaii International International Conference on Systems Science (03-06 January 2005/Big Island, HI). Los Alamitos: IEEE Computer Society Press.
  12. ^ Haddad, D., Walter, S., Ratley, R., & Smith, M. (2001). "Investigation and Evaluation of Voice Stress Analysis Technologies." Rome Laboratory Report (AFRL-IF-RS-TM-2001-7), 18-19.
  13. ^ "IAVSA Home Page". International Association of Voice Stress Analysts. December 19, 2015. Retrieved December 19, 2015. 
  14. ^ nemesysco.com
  15. ^ Haddad, D., Walter, S., Ratley, R., & Smith, M. (2001). "Investigation and Evaluation of Voice Stress Analysis Technologies." Rome Laboratory Report (AFRL-IF-RS-TM-2001-7), 18-19.
  16. ^ Chapman, J. Criminal Justice Department, Corning Community College, New York. "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.
  17. ^ 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.
  18. ^ "Conclusions and Recommendations" The Polygraph and Lie Detection (2003) National Academies Press. p. 212
  19. ^ "The Truth About Lie Detectors (aka Polygraph Tests)". American Psychological Association. August 5, 2004. Retrieved August 14, 2013.
  20. ^ Kovaleski, Serge F. (May 16, 2012). "Trayvon Martin Case Shadowed by Series of Police Missteps". The New York Times. Retrieved May 22, 2012. 
  21. ^ Stutzman, Rene (June 21, 2012). "Tape released of Zimmerman's re-enactment of Martin shooting". Orlando Sentinel. 
  22. ^ "Federal judge approves computer voice stress analysis to monitor sex offenders". Government Security News. March 11, 2014. Retrieved May 27, 2016.
  23. ^ "Statements in rape case allowed in, made 17 hours after voice stress test, judge rules". The Journal Times. June 19, 2014. Retrieved May 27, 2016.