OK, so yer lie detector. It’s been something of a blogosphere hit. And in the comments, we have Nigel, who appears to know something about acoustic signal processing – in the sense of “makes speech recognition systems for Eurofighters”.

It seems that rather than being a signal at a frequency between 8 and 12Hz, the signal you’re interested in is a signal, of that frequency, modulated onto the main signal. So in fact, you could theoretically detect it through a telephone call. I was wrong.

However, that isn’t what Nemesysco’s patent claims, and they vigorously deny that what they are doing is voice stress analysis. It’s not the pitch of any such signal that is discussed in the patent, either; it’s the change in the numbers of thorns and plateaus.

Our acoustic expert says that this could be a way of measuring the signals required for classical VSA, just not a very good one; and anyway, he argues that VSA itself is useless, even if it was VSA they were promising to conduct. And, of course, they deny that this is their methodology. Further, VSA gives only one measurement, one of vaguely-defined stress – not the nine or so Nemesysco claim to get out of this.

Meanwhile, someone who makes the same spelling mistakes as Amir Liberman does showed up in comments to claim there was more, secret technology involved that they hadn’t actually patented. Interestingly, he showed up from the same network as Nemesysco’s Web site. The same network was also the source of a Wikipedia article which got deleted for advertising, in which Nemesysco claimed that their method uses 129 different measurements and isn’t anything like VSA. No, sir. And there weren’t 129 different metrics in their patent…


  1. Nice one, Nigel. Basically it sounds as if we’ve got two separate stages at which false positives can creep in (and false negatives, although in this case I’m less concerned about those). Lying can lead to ‘stress’, but not all stress is caused by lying and not all lying produces stress. And stress can cause detectable vocal fluctuations, but not all fluctuations… and so on.

  2. Nigel’s correct in is his thinking that if you’re going to find the Lippold Tremor anywhere in a telephone signal, then it’ll be present as a modulated harmonic frequency… but,

    I’ve been looking at a couple of Lippold’s original papers from the late 50s and I’m not at all sure that that would work as the tremor appears to be something other than a straightforward subsonic component of speech.

    As best I can can I make out, and my knowledge of human physiology is a bit shaky once we get beyond the realms of neurology (that’s just psychologist for you, we don’t bother with most of the other ‘meat’ stuff), the best analogy I can give is that the Lippold Tremor is something akin to a type of biomechanical ‘mains hum’. It’s not just a function of the voice but present in the musculature generally – one of the papers dealt with the Tremor as a purely physiological presence in the muscles of the wrist.

    As such, its not at all clear whether the Lippold Tremor would modulate into higher frequencies as a harmonic or whether it might exist in the voice only as something akin to a carrier wave. That possibility is something Nigel is almost certainly better placed to assess than me, but if it possible then it may not modulate onto the main signal in quite the way Nigel suggests and we’re back to square one.

    None of this alters that fact that getting from there to a valid assessment of someone’s cognitive processes at an given moment is a pile of tosh.

  1. 1 Dr. Benway strikes again, with Venture Capital « Alternate Seat of TYR

    […] See here. Possibly related posts: (automatically generated)Silence now the soundMcGill Study Shows Videogame […]

  2. 2 G.729 and the welfare state « Alternate Seat of TYR

    […] See here 6 […]

  3. 3 Snake Oil « Alternate Seat of TYR

    […] that the signal it claimed to detect would be transmitted through the telephone system; an expert pointed out that it might be manifested in other ways; eventually we obtained a copy of the patent […]

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: