A new company called "V" is promoting what it calls "Layered Voice Analysis" (LVA), a technology that the company's brochure (http://www.vworldwide.com/downloads/brochures/LVA%20Brochure.pdf) describes as a "Major Investigative Focus Tool designed for professionals in law enforcement, homeland security, armed forces and intelligence and crossed applications in health care industries":
http://www.vworldwide.com/index.html
Note that this limited liability company formerly used the domain name simplyv.org.
See NBC tech reporter I.J. Hudson's recent uncritical reporting on V:
http://www.nbc4.com/technology/2324847/detail.html
It seems that V's reason for being is to find a U.S. market for the "Layered Voice Analysis" software produced by Israel-based Nemesysco Ltd. (http://www.nemesysco.com/), whose software also was used in the Truster and Truster Pro lie detection software formerly marketed by Trustech Ltd.
Let the buyer beware.
Another piece of junk for the crap peddlers to sell.
Its only national security- just another business..
I hope that the purse string holders will be intelligent enough to doubt any company that sells "lie detection' and 'love detection'- but then I am often disapointed.
"V" has caught the attention of the Washington Post, too. See "Software Searches for Truth in Voice Changes" (http://www.washingtonpost.com/wp-dyn/articles/A48907-2003Jul12.html?nav=hptoc_tn) by Ellen McCarthy, 14 July 2003, p. E05.
I found the sidebar on the Washington Post article to be very interesting. Eyeglasses that flash "She thinks you're a dork" or "She thinks you're a hunk" across the inside of the lens when you ask a lady if you can by her a drink. :D :D :D
I received an e-mail message from Dr. Richard D. Parton, V's CEO, who explains that the .org domain was chosen because the .com domain was already taken, and he thought as a start-up, the company's time and attention would be better spent elsewhere than picking domains. Dr. Parton wrote that he wouldn't mind answering any questions I might have, adding that the public benefits from informed debate. The e-mail reply I sent bounced back with an error message that his address no longer exists or no longer accepts mail, so I'm posting my reply here.
Dear Dr. Parton,
Thank you for your reply. I agree with you that the public benefits from informed debate. In my e-mail reply to you, I suggested that we carry out this debate here on the AntiPolygraph.org message board.
Your company has made some extraordinary claims about the capabilities of Layered Voice Analysis. Could you direct me to any double-blind studies that support these claims?
Go getem George
Whenever you decide that a particular technology is not to your liking, no amount of persuasion or research is going to change the way you view things. I have been working with the LVA technology for some time, and I can tell you that in very simple terms; it works. I know that you do not wish to hear this kind of stuff. I also realize that you would prefer to to have me malign the technology as possible because that is your venue. That, too, is okay. As long as we understand one another. Your job is to totally discredit any technology regardless of its utility. Yes, there are blind studies with LVA, CVSA, Polygraph, etc. I just do not think that any of these studies would be of interest to you since your raison d'etre is "bashing" of all deception detection technologies regardless of their validity.
Dr. Albert de Vries
George
You better refute this lying no good sonofa#&*!. I think you should also challenge his credentials and his entire work history. :D
So nice of the good 'doctor' to come down from his mountain and tell everyone his little gizmo 'works'. ::)
True_dat,
The word 'utility' actually means "it scares some people into confessing"
I guess that makes the Doc a 'utility' man, which is a step up from the 'true believer'. They are the worst.
-Although they usually drink the special punch given to them by the Glorious Leader, and are never heard from again-
Hey Doc, which 'deception detection devices' have been found to have validity? Not the polygraph (NAS) and not CVSA (DOJ)!!!
Your not Dr. Gelb's roomate by any chance, are you?
Dr. de Vries,
You write:
QuoteWhenever you decide that a particular technology is not to your liking, no amount of persuasion or research is going to change the way you view things.
The only person regarding whom you can really know whether the above characterization is true is yourself...
QuoteI have been working with the LVA technology for some time, and I can tell you that in very simple terms; it works.
What evidence led you to the conclusion that it "works?"
QuoteI know that you do not wish to hear this kind of stuff. I also realize that you would prefer to to have me malign the technology as possible because that is your venue. That, too, is okay. As long as we understand one another.
I actually would like to hear the evidence. Dr. Parton has acknowledged in an e-mail to me that there are no double-blind studies of LVA. Several of Robert L. Parks's "Seven Warning Signs of Bogus Science" (http://chronicle.com/free/v49/i21/21b02001.htm) are evident in the way LVA is being marketed. Thus, I think you should be able to appreciate why I and others might be skeptical of V's claims regarding Layered Voice Analysis (LVA). Extraodinary claims require extraordinary evidence.
V's key claim regarding LVA that I find to be extraordinary is the claim that LVA can detect deception with an accuracy rate over 90%. Where is the proof? The U.S. National Academy of Sciences states in its report,
The Polygraph and Lie Detection (http://www.nap.edu/books/0309084369/html/), "Although proponents of voice stress analysis claim high levels of accuracy, empirical research on the validity of the technique has been far from encouraging."
V's website states (on the "How it Works" (http://www.simplyv.org/how_it_works.htm) page), "In the late 1990's that all changed with the advent of Layered Voice Analysis. Voice analysis was enhanced by the rapid advancements in personal computer technology. New research was commissioned. When mated with digital sound technology, the results were astounding. Not only were accuracy standards raised above 90% level, but other unexpected results emerged." Where can I find a copy of any report(s) on the research that was commissioned?
The same page on the V website also asserts that, "Mapping the DNA of thought and emotion is now being achieved." Could you refer me to any published research on this purported mapping?
QuoteYour job is to totally discredit any technology regardless of its utility.
No, Dr. de Vries. It is not our job to discredit any technology. If those claiming LVA can detect deception with an accuracy rate of >90% wish to be believed, then it is
their job to prove such claims.
QuoteYes, there are blind studies with LVA, CVSA, Polygraph, etc. I just do not think that any of these studies would be of interest to you since your raison d'etre is "bashing" of all deception detection technologies regardless of their validity.
Dr. Albert ?de Vries
Again, Dr. Parton wrote to me that
there are no double-blind studies of LVA. Perhaps he is mistaken. Would you please provide citations for the "blind studies with LVA..." to which you refer? Have any such studies been published in refereed scientific journals?
George and Friends
You made me proud. Most of the standard bashers came out of the woodwork on this one. I was a little disappointed on your timing though. I figured (no scientific study) you'd be out of the gate much quicker. Maybe I should do a scientific study on that. Hmmm. Although I put little credibility in the CVSA or LVA, I find it disturbing (but not surprising) you guys are already off to the races to chop this guy's character and credentials to pieces. :(
Quote from: Saidme on Aug 01, 2003, 09:57 AMGeorge and Friends
You made me proud. Most of the standard bashers came out of the woodwork on this one. I was a little disappointed on your timing though. I figured (no scientific study) you'd be out of the gate much quicker. Maybe I should do a scientific study on that. Hmmm. Although I put little credibility in the CVSA or LVA, I find it disturbing (but not surprising) you guys are already off to the races to chop this guy's character and credentials to pieces. :(
What does it say for you when even Saidme thinks your little 'lie detector' is no more useful than a snoopy snowcone machine? :'(
True-Dat,
You write:
Quote...What does it say for you when even Saidme thinks your little 'lie detector' is no more useful than a snoopy snowcone machine?...
Actually it means very little...Saidme apparently hasn't realized that that which he is using is no better--which hardly gives much credibility to his assessment of somebody else's quackery.
Now we're cooking. Let's not leave anyone out when it comes to credibility. Attack us all. True_dat is going to have to go back to George's basher school. He/she's a little slow on the up-take. You should know better than to give any hint of a compliment to a polygraph examiner. :D
Thanks for correcting him Anonymous. ;)
Saidme,
Do you think that LVA can distinguish truth from deception, based solely on it technology (meaning no post interrogation)?
I've never used LVA and wouldn't know what one looked like even if it were hooked to George. As I stated earlier in this thread, I put little credibility in CVSA or LVA. I'm sure the next statement from one of you will ask how I can make such an assessment without ever having used it. Because we're in America where I can voice my opinion on anything. I assume LVA training is probably quite similar to CVSA training. Which means, within a very short period of time you can have your secretary out running CVSA and LVA exams. Sounds dangerous. ;)
Saidme,
Does it really matter what kind of machine or system is used?
It's the confession that the proof, right?
Do you really think that the polygraph is any more or less accurate?
Yes I do! I've had several exams over the years where no confession was obtained, yet additional evidence was obtained later which verified the polygraph results. You can say whatever you want but years of success can't be just ignored or thrown away.
saidme,
How many times over how many years= what percent of accuracy?
Quote from: Saidme on Aug 01, 2003, 03:03 PMNow we're cooking. Let's not leave anyone out when it comes to credibility. Attack us all. True_dat is going to have to go back to George's basher school. He/she's a little slow on the up-take. You should know better than to give any hint of a compliment to a polygraph examiner. :D
Just curious..what would make you think I was actually close to giving you a 'hint of a compliment'?
If laughing at how even a polygraph apologist such as yourself turns his back on his own kind is some sort of compliment, feel free to pat yourself on the back alittle more. ::)
:D I worked in the polygraph/voice analysis field in the early 70's and performed double blind analyses of tape recordings of interrogations in both English and in a non-Romance language to ascertain truth or deceit with a prototype voice stress analyzer. The research work was paid for, in part, by several federal agencies. The analyses that I performed resulted in an assessment of 83% accuracy, based on post-interrogation determination of the truthfulness of taped responses.
I felt good about the 83%, it was comparable to polygraph and a whole lot more efficient, but it wasn't good enough to call this technology "lie detection", which is why we continued to call it voice stress analysis.
I read the LVA brochure - very interesting and a quantum leap in the technology. I'd love to know the specifics of their "18 voice parameters", since I was pretty well versed in this stuff once. I find their claims to be a great stretch and am very curious how they achive this. They don't have to worry about patent infringement, I have my own and am not interested in theirs.
Quote from: Some VA Experience on Sep 29, 2003, 08:45 PM:D I worked in the polygraph/voice analysis field in the early 70's and performed double blind analyses of tape recordings of interrogations in both English and in a non-Romance language to ascertain truth or deceit with a prototype voice stress analyzer. The research work was paid for, in part, by several federal agencies. The analyses that I performed resulted in an assessment of 83% accuracy, based on post-interrogation determination of the truthfulness of taped responses.
I felt good about the 83%, it was comparable to polygraph and a whole lot more efficient, but it wasn't good enough to call this technology "lie detection", which is why we continued to call it voice stress analysis.
I read the LVA brochure - very interesting and a quantum leap in the technology. I'd love to know the specifics of their "18 voice parameters", since I was pretty well versed in this stuff once. I find their claims to be a great stretch and am very curious how they achive this. They don't have to worry about patent infringement, I have my own and am not interested in theirs.
Double blind eh? Where is the study published? I would be most interested in understanding it (especially being an EE).
-Marty
Which brings up an interesting point: anyone who has a background in math/science/engineering is going to be skeptical of unsupported claims about the efficacy of the polygraph. My guess is that the "Dr." who made a post is a Ph.D. - in a non-science related area, like psychology, education, and so on. The EdD's, "doctor" of education, is the lowest, I mean the absolute lowest, form of any doctorate, and they tend to overuse the "Dr." title. But I digress.
Any "Dr." who makes claims about how accurate or reliable some instrument is surely knows those claims are going to be challenged, and that is part of the scientific method. Claims without supporting evidence are BS, and that is a fact.
Marty wants to know where study was published. The only publication I am aware of was a Technical Report to the US Army's Limited Warfare Laboratories in 1973. I used to have a copy and if I find it, can provide the document number, but if you're handy retrieving federal documents from their archive services it should be locatable. If its interesting, there were several EE's associated with this sudy, as well as Psychology PHD's (and one ABD). And, of course, appropriately qualified personnel from several selected federal agencies who had an interest.
Quote from: Rick Fuller on Sep 30, 2003, 04:02 PMMarty wants to know where study was published. The only publication I am aware of was a Technical Report to the US Army's Limited Warfare Laboratories in 1973. I used to have a copy and if I find it, can provide the document number, but if you're handy retrieving federal documents from their archive services it should be locatable. If its interesting, there were several EE's associated with this sudy, as well as Psychology PHD's (and one ABD). And, of course, appropriately qualified personnel from several selected federal agencies who had an interest.
Rick,
Thanks. Unfortunately, having only worked in the private sector, I'm ill equiped to search this. It's likely some others here could assist though. Being an EE by profession, I am most interested in how this was approached. Especially given the limited technology back then. These days the most sophisticated DSP is dirt cheap.
-Marty
See Colin R. Johnson's EE Times article, "Lie detector glasses offer peek at future of security" for recent news on "Layered Voice Analysis":
http://www.eetimes.com/story/OEG20040116S0050
A lively discussion of this article is to be found on Slashdot.org here:
http://slashdot.org/articles/04/01/20/1857249.shtml
What a bloody Joke!!!!!!!!
The Software in question was originally marketed in Israel as a child's TOY!! (Ex-Sense Pro) and sold in toystores and bookstores without that much success.
Please keep in mind that here in Israel, we also use handwriting analysis, amulets, and magic spells (blessings) as a matter of routine within our government agencies.
The Hebrew word for "sucker" is "freir", and only freirs would be taken in by such deceptive marketing!
Okay, if this technology is as good as the creator claims, then can an insurance company deny a claim based on the results of the LAV? How do the results effect law enforcement? ??? :o
Hey George,
Why don't you undergo exactly the same questioning with LVA that you had with the polygragh?
I think it would be really interesting to hear your opinions on the whole experience from a firsthand perspective.
Would that be possible?
What purpose would be served by such an undertaking? I think it would be about as interesting as posing the questions to a Magic 8-Ball (http://www.mattelgames.com/magic8/flash_index.asp).
Instead, those claiming that Layered Voice Analysis is a reliable test for deception should provide proof, something they have thus far utterly failed to do.
Well it would give you the opportunity to compare the responses to your answers like for like.
It would also protect you from a charge of being guilty of "contempt prior to investigation" which is your current position from an epistemiological perspective.
I don't know whether this stuff works or not so to hear a first hand report of a direct comparison between these two systems would have been helpful.
But I do understand the difficulty from your own personal stance. Should this equipment actually vindicate your polygraph experience where would you go from there? ;)
Quote from: A reasonable suggestion on Jun 16, 2004, 10:55 AMWell it would give you the opportunity to compare the responses to your answers like for like.
It would also protect you from a charge of being guilty of "contempt prior to investigation" which is your current position from an epistemiological perspective.
I don't know whether this stuff works or not so to hear a first hand report of a direct comparison between these two systems would have been helpful.
But I do understand the difficulty from your own personal stance. Should this equipment actually vindicate your polygraph experience where would you go from there? ;)
Right, that would make George a three time loser. And it would strain anyone's credulity to think he was anything but the liar he has been diagnosed as being on both previous polygraph tests.
To Neutral Observer
I hadn't thought of it that way. I actually meant vindicate George by results agreeing with his claim that he was telling the truth. To be believed by something you don't believe in would be a bit awkward to say the least.
Thanks for pointing that out, it would take someone with considerable cajones and integrity to have taken up my reasonable suggestion in these circumstances :-X
Quote from: a reasonable suggestion on Jun 19, 2004, 05:13 PMTo Neutral Observer
I hadn't thought of it that way. I actually meant vindicate George by results agreeing with his claim that he was telling the truth. To be believed by something you don't believe in would be a bit awkward to say the least.
Thanks for pointing that out, it would take someone with considerable cajones and integrity to have taken up my reasonable suggestion in these circumstances :-X
And since George has neither cajones nor integrity, you can rest assured he will not be taking any more tests.
Quote from: A reasonable suggestion on Jun 16, 2004, 10:55 AMWell it would give you the opportunity to compare the responses to your answers like for like.
But such a small study would be statistically meaningless and would reveal nothing about the validity of Layered Voice Analysis.
QuoteIt would also protect you from a charge of being guilty of "contempt prior to investigation" which is your current position from an epistemiological perspective.
If you review this message thread, you'll find that I have, in fact, investigated Layered Voice Analysis. And I found no credible evidence to support the claims of those marketing it. If you are aware of relevant information that you think I have ignored, please direct me to it.
QuoteI don't know whether this stuff works or not so to hear a first hand report of a direct comparison between these two systems would have been helpful.
But the experiment you suggested would reveal nothing about the validity of Layered Voice Analysis, not only because of the small sample size, but also because of the virtual impossibility of independently verifying ground truth in a screening scenario such as you proposed: the questions asked in pre-employment screening polygraph examinations typically involve using and selling drugs, espionage, and sabotage. But how can one prove that one has never done these things? You cannot prove a negative.
A more revealing experiment that I might be willing to partake in is this: on videotape, I will flip a coin 100 times, with the result being shown on camera. After each flip, I will make two statements: 1) The coin is heads up; 2) The coin is tails up. These statements will also be audio recorded.
The purveyors of Layered Voice Analysis will receive the audio recording, perform an analysis of my voice, and determine the result of each coin toss. The results will then be placed on-line for the edification of all.
QuoteBut I do understand the difficulty from your own personal stance. Should this equipment actually vindicate your polygraph experience where would you go from there? ;)
It's not concern about the possible results of the experiment that you suggested which leads me to conclude that it would not be worthwhile, but rather the fact that the results would shed no light on the validity of Layered Voice Analysis.
By contrast, the experiment I have suggested would produce results that could readily be compared against ground truth and from which some logical inference(s) might be possible.
If George gives them his audio recording and they do the LVA test, it would show that he is not affraid to find out the truth, even if it isn't a full blown scientific test. I for one would like to see the results. I have been hearing a lot of second hand stories about the amazing results some of my police friends have been getting using the LVA software.
QuoteIf George gives them his audio recording and they do the LVA test, it would show that he is not affraid to find out the truth, even if it isn't a full blown scientific test.
An audio recording of Mr. Maschke's voice is available on the home page of this website. Go ahead and give it a try. Mr. Maschke may very well oblige you, but why should he. As you note it isn't a full blown scientific test. The only science to it is that it records the unexplored world of vocal stress patterns.
QuoteI have been hearing a lot of second hand stories about the amazing results some of my police friends have been getting using the LVA software.
I would venture that these "amazing results" are the fruits of deception. It is not that the "test" works. It is that the criminals providing a confession believe it works.
If you are interested, I have for sale, beach-front property in Arizona.
Would normal pitch or patterns of a person's voice be construed as stress? take an adolescent whose voice pattern can change constantly because of growth and hormonal changes. so where is the considered baseline on where the voice is considered normal and considered stressed? sounds like a guessing game to me.
Quote from: gelb disliker on Dec 24, 2005, 09:32 AMWould normal pitch or patterns of a person's voice be construed as stress? take an adolescent whose voice pattern can change constantly because of growth and hormonal changes. so where is the considered baseline on where the voice is considered normal and considered stressed? sounds like a guessing game to me.
As with polygraphy, there is no peer-reviewed research supporting the validity of "Layered Voice Analysis" for lie detection, love detection, or any other purpose for any age group.