Stockholm professor speaks in public about the "Illusion of lie detection"

Francisco Lacerda, professor of phonetics, spoke during the conference about the controversial nature of LVA-technology, which is being used in some countries to screen applicants, passengers or customers in areas like security, medicine, technology and risk management.

In the paper which is already available online Lacerda posits that “a scientific evaluation of this technology and of the principles on which is relies indicates that it is neither valid or reliable.”

Professor Lacerda’s research on the Layered Voice Analysis technology produced by Nemesysco Ltd. of Netayna, Israel, which is being tested by municipal governments in the United Kingdom as a means of weeding out fraud among benefits applicants, has previously landed him in trouble.

At the end of 2008 Lacerda, along with colleague Anders Eriksson, professor of phonetics at the University of Gothenburg, was threatened with legal action after the publication of a scientific article in the International Journal of Speech Language and the Law condemning the use of lie detectors.

The Israeli company Nemesysco, which manufactures lie detectors based on patented LVA technology, wrote to the researchers' publishers that the researchers may be sued for libel if they continue to write on this subject in the future.

The article, "Charlatantry in forensic speech science", was subsequently withdrawn by British publisher Equinox and Lacerda was warned he could be sued for defamation if he wrote on the subject again.

The response from the university, academic community and general public was intense.
“For weeks I could deal with nothing else,” admits Professor Lacerda. “Journalists and bloggers from around the world contacted me about the story. Six months later I still receive emails about it from people interested.”

In May even the Royal Swedish Academy of Sciences weighed in, expressing outrage at the publisher’s decision to withdraw the peer-reviewed paper, calling the incident “a serious assault on research freedom.”

The Royal Swedish Academy of Sciences regards what has happened as a serious matter and said in its statement: “Incidents of this kind are a threat to research freedom and, by extension, to the free dissemination of information in society. Threats to sue must not be used to restrict scientific discussion.”

Despite the threat of legal action, Lacerda says it is important to continue challenging such dubious science as LVA technology.

“LVA-technology is a crude and absurd processing technique from the perspectives of acoustic phonetics and speech signal processing. It lacks a theoretical model linking its measurements of of the waveform with the speaker’s emotional status but the measurements themselves are so imprecise that they cannot possibly convey useful information” explains Lacerda.

Furthermore, Lacerda claims that it will not make any difference if Nemesysco “updates” in its LVA-technology.

“The problem is in the concept’s lack of validity,” says Lacerda. “Without validity, so-called ‘success stories’ of ‘percent detection rates’ are simply void. Indeed, these ‘hit-rates’ will not even be statistically significant different from associated ‘false-alarms’, given the method’s lack of validity.”

As far as Professor Francisco Lacerda is concerned, “until proof of the contrary is given, LVA-technology should be simply regarded as a hoax and should not be used for any serious purposes.”

Fonetik 2009
The Fonetik 2009 conference took place at Stockholm University 10-12 June 2009. www.ling.su.se/fon/fonetik_2009/program.html

Text and interview: Jon Buscal