Hobson, Mayew and Venkatachalam’s paper, Analyzing Speech to Detect Financial Misreporting, is just the last of a series of flawed studies by Mayew and Venkatachalam. The authors insist in using Nemesysco’s LVA technology and give the impression that this is as an emerging speech analysis technology based on Nemesysco’s proprietary secrets. In reality the LVA principles were described in Liberman, A. (2003), US patent No. 6,638,217 B1. Although the ad hoc thresholds used in the program may have been changed since then, the patent unequivocally demonstrates that LVA principles are absurd and incapable of extracting any useful information from the waveforms it is supposed to analyze (see Lacerda (2012), “Money Talks: The Power of Voice – A critical review of Mayew and Ventachalam’s The Power of Voice: Managerial Affective States and Future Firm Performance”, for an explanation of why the LVA technology cannot work). Given the irrelevance of the LVA basic variables, further processing of the measures cannot produce any sensible results (unless information would be added during the processing, which is not the case). The so-called “proprietary secrets” are most likely no more than Nemesysco’s pseudo-scientific wording, circular arguments and incompetent descriptions of the speech production process that are supposed to lead naïve customers into the belief that there are indeed “proprietary secrets. Mayew and Venkatachalam have failed to see through the ungrounded claims of the LVA vendors. As a consequence, Mayew and Ventachalam have so far published a series of inconclusive papers because their results are critically dependent on the validity of LVA technology.
As academic researchers, Mayew and Venkatachalam’s uncritical acceptance of a commercial “black-box” is per se the kind of mistake that researchers should be trained to avoid. Unfortunately, Mayew and Venkatachalam’s assumption of LVA’s validity has surprisingly passed the review hurdles of several finance-oriented publications, conveying the bizarre impression that repeating series of void results may eventually turn them into valid results. However, whereas accommodation to repetition pressure may be an interesting psychological phenomenon and a driving force in the world of finance, where prices and product acceptance are affected by the number of interested customers, scientific explanations must be based on logical and grounded arguments that stand by themselves, independently of superficial customer opinions or market expectations. In summary, circular references do not increase the explanatory power or validity of a claim and any proper speech analysis must be grounded on scientific signal processing principles that stand public scrutiny, rather than on obscure “knowledge” of self-promoted “researchers” or sellers.
Obviously, Hobson, Mayew and Venkatachalam lack competence in the areas of speech analysis and signal processing but they should have been skeptical and demanded convincing answers to pertinent questions about the working principles of the LVA technique. They should also be aware that although correlations may be a useful exploratory tool in epidemiological studies, correlations, even if significant, do not by themselves prove or demonstrate anything unless supported by plausible and adequate models. In the case of an ad hoc constructed algorithm, like LVA, it does not even make sense to explore the algorithm’s validity using correlations. Validity must be demonstrated by the manufacturers’ principled arguments, not by the sort of inconclusive statistical fishing expedition that Mayew and Ventachalam appear to have engaged into. However, because the LVA technology is not supported by any reasonable or even plausible principle, the series of self-references in methodologically flawed papers and the excuse of “proprietary secrets” only fuel the notion that LVA technology is no more than just a sham. Thus, unless Mayew and Ventachalam (or anyone else selling or using LVA-based technology) can independently demonstrate that the processing carried out by LVA provides meaningful emotional information, the technology must be seen as an irrelevant “digital dowsing rod” and it makes of no sense to discuss its results or their implications at this point.
Of course, Nemesysco is not the only company trying to sell “advanced” technology based on pseudo-scientific analyses of speech. There seems to be an expanding market for bogus analyses backed up by aggressive propaganda exploring fiction and myths that may be appealing for a public lacking basic competence in speech processing and phonetics. This can only be stopped by an educated cautious and skeptical public that demands principled evidence for the seller’s claims. Scientists cannot expose all the pseudo-scientific nonsense in society but they have the responsibility of at least not endorsing it, like Mayew and Ventachalam did by adopting a “black-box” that there is virtually no independent reason to believe in. They should be encouraged to perform a scientific reanalysis of all their speech materials. A proper analysis of the speech materials may or not corroborate the authors’ hypothesis but it will, above all, produce results that are worth considering. By insisting to use a technology that they do not grasp and for which there are no scientific grounds, Mayew and Ventachalam are contributing to a mockery of financial research and, by extension, undermining serious science.
References
Lacerda (2012), “Money Talks: The Power of Voice – A critical review of Mayew and Ventachalam’s The Power of Voice: Managerial Affective States and Future Firm Performance”, http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-74478
Liberman, A. (2003). US patent Patent No. 6,638,217 B1. http://www.freepatentsonline.com/6638217.pdf
Department of Linguistics, Stockholm University http://www.ling.su.se
Comment by Francisco Lacerda — March 13, 2012 @ 1:58 pm
(This comment was initially posted at http://blogs.law.harvard.edu/corpgov/2012/01/13/analyzing-speech-to-detect-financial-misreporting/, as shown above, but deleted by the moderator about 1 hour later)
Phonetics at Stockholm University Blog 
We disagree with your assertion that our papers are flawed (a detailed response is located at http://faculty.fuqua.duke.edu/~vmohan/bio/files/Lacerdaresponse.pdf). Your latest critique (Lacerda 2012, referred above) is similar to your previous critiques (Eriksson and Lacerda (2007) and Lacerda (2009)). Our understanding of your criticism is that you base your conclusions about LVA on your evaluation of Nemesysco’s patent documents. There are at least two reasons why such an evaluation may be inconclusive. First, the patent information analyzed is incomplete. Patents rarely include all source or object code. Further, Nemesysco has publicly stated that the patent documents cover roughly 5% of the current technology. Second, we and others have empirical data, some published in peer-reviewed journals, that counter your view. Your view of LVA as fundamentally flawed based upon this patent information allows you to reject all future empirical evidence to the contrary. This argument is a tautology, and appears to us to run counter to the very nature of the scientific process.
For scientific discovery and learning to progress, it is important that we question and debate the theories and findings of others. We feel we have undertaken unbiased, empirical research into LVA and important correlated variables. However, you reject this analysis without evaluating it on its merits. The validity and association of LVA variables is empirically testable. We undertake just such tests in Mayew and Venkatachalam (2012) and Hobson, Mayew and Venkatachalam (2012). Your statement that we have accepted the “black box” software without reservation is far from true. Rest assured that the referees and the editors of the journals in which we publish are aware of your criticisms of LVA and were equally skeptical, as were we. As a result, we have conducted several analyses to convince ourselves and others that the LVA variables are not simply random. First, we provide evidence in Mayew and Venkatachalam (2012) that the LVA variables that we use are correlated with various acoustic features commonly studied in the measurement of emotion from voice. Second, in Hobson, Mayew and Venkatachalam (2012) we use experimental subjects to generate a sample of truth-tellers and misreporters and examine whether the LVA variable that captures cognitive dissonance has construct validity. Finally, we have replicated the main archival results in Mayew and Venkatachalam (2012) showing the association between the LVA emotion metrics we use and stock prices using an independent and more recent sample. As empiricists, the strength of a result is determined by how it stands the test of time. We welcome more empirical scrutiny of the LVA measures in order to determine their construct validity in other settings.
As academics we should be entitled to our views and opinions but express them in a manner that facilitates scientific progress. Your review appears to cast aspersions on the integrity on us as academics without any substantive empirical basis. Finally, we have no financial interests in Nemesysco and the purpose of our papers is not to advocate LVA or any other software. We see our work as examining “The Power of Voice” and not “The Power of LVA.”
Thank you very much for your reply. I apologize for being so slow responding to it. I wrote a more extensive discussion on a new post on this blog (“Money Talks: The Power of Voice — Comment on William J. Mayew and Mohan Venkatachalam’s reply”). It is essentially repeating what I wrote earlier, hopefully clarifying some aspects. In fact, there is no science behind LVA, so there is nothing new to talk about.
I understand that you adopted an open-minded attitude when using Nemesysco’s LVA-technology in your work but I think it was a mistake to give Nemesysco’s software such an importance as to consider it as a possible tool in academic research. This LVA-technology is one of the clear cases that can be dismissed as bogus right from the company’s own documentation. It is like testing new implementations of perpetual machines. It is enough to analyse the documentation to predict the devices’ behaviour. Also in the case of LVA, what you and others are looking at are statistical accidents that have nothing to do with the detection of emotions. The system does not know what it is doing and looking at correlations does not prove that it does. It is a bluff that may fascinate people without training in scientific methodology. Just like in the case of magic tricks, the outcome is an illusion whose underlying mechanisms may be difficult to spot even for trained scientists. The difference is that in the entertaining business everybody knows, and admires, the magician’s tricks whereas charlatans want you to believe that they actually have supernatural powers.
Let us be sceptical while waiting for Nemesysco’s demonstration of LVA-technology’s underlying principles. Unless there is a solid demonstration of first principles justifying the workings of the LVA-technology, I am afraid that all you have done is in fact demonstrating “The Power of LVA”, not “The Power of Voice”, which was not very much power after all.
Of course, the safest remedy for this is to correct the error and perform a proper analysis of the speech materials. I look forward to learning about your reviewed results.
What’s next Lacerda? Are you going to suggest there is no polygraph either,that our brain has no effect on our body and that the earth is really flat? You are the one capitalizing from writing this bogus!You know as well as these real academics that researching the speech of northern Swedish deer herders does not give you credentials to criticize LVA.
—————————————————
Moderator’s note:
More information about Sara Danielle
IP: 79.181.149.249, bzq-79-181-149-249.red.bezeqint.net
E-mail: sara_daniel@hotmail.com
URL:
Whois: http://whois.arin.net/rest/ip/79.181.149.249
Received on April 24, 2012 @ 14:33.
No further comments.