Wednesday, October 15, 2014

No need to mischaracterize voice biometrics in call centers

Amidst all the attention banks are receiving over the use of voice biometrics to prevent fraud, It's worth noting a couple of things.

First, according to the widely linked AP article, "The technology, sometimes called voiceprinting, is aimed at bad guys rather than legitimate customers, but legal and privacy experts alike still have reservations about the practice." So, the systems in place seem to work by collecting information on known and suspected fraudsters and placing them on a watchlist (listenlist?). This makes sense. Technically, it's far easier to be on the lookout for a handful of persons of interest than it is to make a positive ID on every single caller.

Second, there are a lot of way over-hyped headlines out there that make it appear as though financial institutions are collecting voice biometric information on unwitting customers on a vast scale.

Take:
Some Banks Collect Voiceprints During Service Calls to Identify You (Salon) 

Technically, this Slate headline isn't even true since according to the source it cites, the voiceprints are being used to identify fraudsters, not to verify the identities of account holders.

Then there's this.

Banks Harvest Callers' Voiceprints to Fight Fraud, which is the unfortunate headline of the very AP article that acknowledges that the systems function as criminal watchlists rather than a "harvest" of biometric information.