The VSA Industry has been somewhat stagnant for the past decade. When Jean-Louis Gouin (Alpes-Software) developed Diogenes Lantern for Bill Ames, a new era began.
Sadly, Bill Ames passed away several years ago. Two of his erstwhile employees assumed the rights to continue distributing Diogenes and they employed Alpes-Software to re-label Diogenes as TDT. Alpes retained copyright ownership of the Diogenes program.
TDT (Truth Detection Technologies)- the name is somewhat of a misnomer as they have not produced any technology, despite their bold claims on their website.
In late 2009 I (Clifton Coetzee) made contact with Jean-Louis Gouin and we began a collaboration that has revolutionised the VSA industry.
Before I continue, it is important that one never confuses LVA with traditional VSA.
In my years of patient review of DOD technologies, I have found that LVA has reliability less than chance. Therefore I dismissed it totally in 1998, 200, 2002 and again in 2004. Since 1998 many LVA renditions have come to the marketplace:
Truster; Truster Pro; Tipi; Vipre/Vypre; SVX13; SVX13A; TVSA13;
The only true VSA applications as at current time ( May 2011) are AVSA Pro; CVSA; PSE5128 and TDT (Diogenes)
Interestingly, Diogenes Lantern was the only vsa program to have received a modicum of validity in scientific validation reviews, almost a decade ago.
The good news is, that Jean-Louis Gouin wrote Diogenes and it is the grounding for AVSAPRO. The spectrograph capture window in Diogenes and the general layout will be recognised in AVSAPRO, but that is where all similarity ends.
Where Diogenes (now TDT ) was a manual vsa program, AVSAPRO is fully automated with evolutionary features.
No longer does an examiner have to cut and highlight or tab the required CQ / RQ responses. AVSAPRO is equipped with validated question protocols and auto captures the responses required. Each question in a protocol is rolled onto the screen only when the preceding question has been asked, answered and captured. Questions can be re-asked without affecting the numerical allocation.
AVSAPRO automatically rotates the RQ's in subsequent charts (exams)
AVSAPRO maintains consistent cadence control, which in turn produces consistently reliable results. At the end of every question, the examiner habitually presses the response key, which emits an audible answer cue for the examinee 1,5 seconds later.
As the examinee has already recognised the question approximately 1-1,5 seconds before quesion terminates, the required Onset Delay phase of 2-2,5 seconds has been satisfied.
AVSAPRO is equippped with extremely versatile and unique filing alternatives. Tests can be recorded into any directory on the pc or direct to removable media.
Full recall is available via either of two independent methods.
Tests can be run in auto mode or manual mode. Scoring may be effected manually (examiner) or by the neural network processor.
AVSAPRO auto scoring does not involve random application of unproven theories or electronic recognition of tone or pitch. AVSAPRO has been trained by the neural network according to Expert Human scoring of 000's of voice wavs, blind scored and rescored several times. Many known outcome solutions have been utilised to train the neural network.
It can be said that AVSAPRO is the first DOD technology ever to utilise Artificial Intelligence (AI).
Futue versions of AVSAPRO will make provision for scoring of multiple word utterance to a Dichotomous question. GSR and Cardio functions are to be added.
The future of DOD is AVSAPRO.
Continuing the AVSAPRO evolution. In late 2014, Clifton and Jean-Louis began to develop a ne web based application, AvsaPro Global.
AVSAPRO Global is the Gold Standard for a world standardisation of Voice Screening and Testing.
Global version will be freely downloadable from the internet. Users can choose the type of question template required; either for Pre-Employment Screening; Periodic Honesty Screening, or Felony Issues such as theft or fraud.
Globa; version has a question library to assist users in question selection to match the Issues or Screenings. The questions are colour coded and can only be selected for a matching colour field.
APA validated question constructs are utilised to maintain accuracy.
Cadence(timing) is controlled and the tests are easily run, by following simple instructions in the Facilitators Manual.
Ultimately a simplified report is produced. The tests and screenings are scored by a neural network processor, to deliver a high degree of consistency and reliability.
The human involvement has been further removed in order to demistify and decontaminate tests and results.
While the App is free to download, users must register online and pay a nominal fee to purchase tests (licences) in batches of 1, or 5, or 10, or 50, or 100.
Global version will cater mainly for high volume users who require accuracy and consistency.
However, Accredited Professional Examiners will have access to the Professional section where there is freedom question construction, but template structure is maintained to produce simplified easy to understand reports.
No longer will anyone have to employ expensive specialists and no longer will anyone have to pay exorbitant fees for specialist training.
Reliable Screening and Testing of personnel is about to become very affordable.
AVSAPRO Global Gold Standard
www.avsaproglobal.com
Tuesday, May 17, 2011
Wednesday, December 23, 2009
Voice Stress Analysis (Wikipedia Excerpt)
PRINCIPLES & ORIGINS
VSA is based on the subsonic components of human voice not audible to observers, now known as the Lippold Tremor. In 1957, Olaf Lippold discovered this physiological tremor in the human voice in the 8-12 Hz range. Lippold, Redfearn and Vuco began exploring the correlation between muscle activity and stress, and found that when the fight or flight response presents in a person, one of the psycho-physiological responses that manifest, is the involuntary tensing of the 'soft' striated muscles, particularly, the laryngeal muscles. Under normal circumstances, the laryngeal muscle is relaxed, producing recorded voice at approximately 12Hz. Under stress however, the tensed laryngeal muscle produces voice significantly lower in pitch.
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 three, under Dektor Counterintelligence and Security, Inc., manufactured the PSE 1000 and later the PSE 2000. The first supplier of VSA technology was Dektor. Dektor manufactured the PSE 1000, an analogue machine, that was later replaced by the PSE 2000.
The National Institute Of Truth Verification (NITV, West Palm Beach) then produced and marketed a digital application based on the McQuiston-Ford algorithm in April, 1997.f> In the past 10 years VSA has been used primarily in digital applications: Digital Voice Stress Analysis (D-VSA). The primary suppliers are NITV-CVSA; Dektor-PSE5128, Diogenes-Lantern and Baker-FVSA.
The primary use of VSA is in the arena of 'Detection Of Deception'. As with the polygraph, Manual VSA technology is inert and has no artificial intelligence component. It can be said that both technologies are equally reliable in determining a person's truthfulness under similar circumstances. Both technologies record data that they were designed to do. It is the use of that data as a means for lie detection that remains controversial.
Avsapro is an automated VSA system utilising a neural network (Artificial Intelligence) Avsapro renders all other VSA programs to be redundant and obsolete.
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.
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.
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.
Traditional VSA utilizes the McQuiston-Ford algorithm and this is the technology developed in the USA for the US Defence Agencies and is used by US Law Enforcement agencies.
There are no known physical countermeasures for VSA. Conversely, 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%.
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.
Methodology and accuracy
The McQuiston-Ford algorithm used for Voice Stress Analysis is reliably accurate. 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.
Polygraph-only associations have disputed the accuracy of VSA, although many accredited polygraphists have trained in the use of VSA and use VSA to good effect. 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.
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 Clifton Coetzee and Jean-Louis Gouin developed Avsapro, an automated VSA system that eliminates all common examiner errors. Avsapro built in cadence features provide consistency in scoring that no other VSA system can emulate.
VSA is based on the subsonic components of human voice not audible to observers, now known as the Lippold Tremor. In 1957, Olaf Lippold discovered this physiological tremor in the human voice in the 8-12 Hz range. Lippold, Redfearn and Vuco began exploring the correlation between muscle activity and stress, and found that when the fight or flight response presents in a person, one of the psycho-physiological responses that manifest, is the involuntary tensing of the 'soft' striated muscles, particularly, the laryngeal muscles. Under normal circumstances, the laryngeal muscle is relaxed, producing recorded voice at approximately 12Hz. Under stress however, the tensed laryngeal muscle produces voice significantly lower in pitch.
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 three, under Dektor Counterintelligence and Security, Inc., manufactured the PSE 1000 and later the PSE 2000. The first supplier of VSA technology was Dektor. Dektor manufactured the PSE 1000, an analogue machine, that was later replaced by the PSE 2000.
The National Institute Of Truth Verification (NITV, West Palm Beach) then produced and marketed a digital application based on the McQuiston-Ford algorithm in April, 1997.f> In the past 10 years VSA has been used primarily in digital applications: Digital Voice Stress Analysis (D-VSA). The primary suppliers are NITV-CVSA; Dektor-PSE5128, Diogenes-Lantern and Baker-FVSA.
The primary use of VSA is in the arena of 'Detection Of Deception'. As with the polygraph, Manual VSA technology is inert and has no artificial intelligence component. It can be said that both technologies are equally reliable in determining a person's truthfulness under similar circumstances. Both technologies record data that they were designed to do. It is the use of that data as a means for lie detection that remains controversial.
Avsapro is an automated VSA system utilising a neural network (Artificial Intelligence) Avsapro renders all other VSA programs to be redundant and obsolete.
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.
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.
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.
Traditional VSA utilizes the McQuiston-Ford algorithm and this is the technology developed in the USA for the US Defence Agencies and is used by US Law Enforcement agencies.
There are no known physical countermeasures for VSA. Conversely, 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%.
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.
Methodology and accuracy
The McQuiston-Ford algorithm used for Voice Stress Analysis is reliably accurate. 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.
Polygraph-only associations have disputed the accuracy of VSA, although many accredited polygraphists have trained in the use of VSA and use VSA to good effect. 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.
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 Clifton Coetzee and Jean-Louis Gouin developed Avsapro, an automated VSA system that eliminates all common examiner errors. Avsapro built in cadence features provide consistency in scoring that no other VSA system can emulate.
Voice Stress Analysis
Voice Stress Analysis (VSA) is a lie detection technology- and uniquely deployed as such- which is newer than the polygraph, but still controversial.[1]
VSA technology records 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'.[2]
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 lies 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 by polygraph-industry initiated research. 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.[3][4]
For example, a 2005 study found the TrusterPro LVA system to be invalid for detection of guilty knowledge. Research commissioned by the Department of Justice and conducted by AFRL (Air Force Rome Labs), as well as several other researchers, also suggested less accuracy rates for the same system, marketed in the US under a different name ("Vericator").
The skill and experience of the VSA Examiner is of utmost importance.[5]
LVA - Layered Voice Analysis technology- known as LVA or VRA - is finding use as a screening tool in the UK, in which recipients of jobless benefits are faced with the 'threat only' of a test, and would consequently face more scrutiny if they "failed".
The LVA test itself has accuracy levels less than chance (50%) but the mere threat is used in this instance. [6]
LVA trials conducted by private Polygraph & VSA Instructor/Examiners in South Africa produced reliability levels of <30 a="" and="" association="" consequently="" for="" href="http://en.wikipedia.org/wiki/Voice_stress_analysis#cite_note-6#cite_note-6" is="" lva="" membership="" non="" of="" polygraph="" qualifying="" sa.="" stress="" technology="" the="" title="" to="" voice="">[7]
, the consumer version of the LVA technology, is available in different products and produces non-useful readings such as 'love' and 'Embarrassment' (not relevant in DOD applications).[8]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]. http://www.polyvsa.co.za http://www.avsapro.com
VSA technology records 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'.[2]
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 lies 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 by polygraph-industry initiated research. 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.[3][4]
For example, a 2005 study found the TrusterPro LVA system to be invalid for detection of guilty knowledge. Research commissioned by the Department of Justice and conducted by AFRL (Air Force Rome Labs), as well as several other researchers, also suggested less accuracy rates for the same system, marketed in the US under a different name ("Vericator").
The skill and experience of the VSA Examiner is of utmost importance.[5]
LVA - Layered Voice Analysis technology- known as LVA or VRA - is finding use as a screening tool in the UK, in which recipients of jobless benefits are faced with the 'threat only' of a test, and would consequently face more scrutiny if they "failed".
The LVA test itself has accuracy levels less than chance (50%) but the mere threat is used in this instance. [6]
LVA trials conducted by private Polygraph & VSA Instructor/Examiners in South Africa produced reliability levels of <30 a="" and="" association="" consequently="" for="" href="http://en.wikipedia.org/wiki/Voice_stress_analysis#cite_note-6#cite_note-6" is="" lva="" membership="" non="" of="" polygraph="" qualifying="" sa.="" stress="" technology="" the="" title="" to="" voice="">[7]
, the consumer version of the LVA technology, is available in different products and produces non-useful readings such as 'love' and 'Embarrassment' (not relevant in DOD applications).[8]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]. http://www.polyvsa.co.za http://www.avsapro.com
Monday, December 21, 2009
VSA Training
Voice Stress Analysis ( VSA ) is a user friendly technology and is extremely reliable in the hands of a skilled examiner-operator. Lie Detection just took a major leap forward with the provision of expert training available in South Africa. Clifton Coetzee, Christina Scoging and JP Roux are the experts. Visit http://www.polyvsa.co.za
Visit http://www.avsapro.com
Voice Stress Analysis - VSA
Voice Stress Analysis (VSA) as a lie-detection tool has become extremely popular amongst forensic investigators and is steadily replacing the polygraph. Whilst polygraph averages out data from three physiological sources and therefore has a fairly wide margin of tolerance for below par Examiners, VSA uses only one such parameter and so there is lttle or no tolerance for operator error. It is extremely important that the operator receives training from an Instructor that has many years of experience and a solid background in Psychophysiological Detection Of Deception. The general public should be aware and exercise caution when dealing with VSA operator-examiners. They need to be 100% sure that the operator-examiner has been trained and is a member of a reputable, locally based Association. They need to be even more sure that the operator is not using layered voice analysis (LVA), which is has accuracy levels way below chance. There is no reputable PDD association in South Africa that will admit LVA operators as members. Forensic voice stress analysis technology is the future. For training in South Africa, contact Christina Coetzee and Clifton Coetzee via cliff@avsapro.com (www.avsapro.com and www.polyvsa.co.za )
Subscribe to:
Posts (Atom)
