
Now a company wants to use a person's voiceprint as way to secure credit card payments. So instead of giving out their card number, shoppers will use their voice. The developers claim that their technology could help reduce identify theft and allow account holders to shop by mobile phone, even when they're nowhere near an Internet connection.
"It's a way of making payments for anything, anywhere with complete security and no concern. As long as they have a telephone they can do a transaction with Voice Pay," said Nick Ogden, founder and CEO of Voice Pay, which launched 18 months ago and is based in Jersey in the U.K.'s Channel Islands.
At the heart of Voice Pay is a speech authentication algorithm developed by Dublin-based Voice Vault. On the surface, the system may seem a little like those voice dialing systems that exist on mobile phones. Say, "call Mary" and the phone automatically dials Mary's number.
But this technology is more sophisticated. It analyzes 117 voice parameters that are wholly unique to an individual's vocal chords and the shape of the inside of the mouth and nasal cavity. Even a voice impersonator, who might sound like the user, cannot mimic certain subtleties naturally present in a person's voice, said Ogden.
To use the voice payment system, a user has to first set up an account with Voice Pay. To do so, they call the company from a cell phone, choose a username and password, and provide credit card information. Next, the shopper provides a voiceprint by repeating a series of randomly generated numbers.
Authentication happens at the time of purchase. For example, a website could have a Voice Pay icon that the shopper would click to make a purchase. The click would launch the Voice Pay site, which, once the shopper had logged in, would call the customer's cell phone.
A person could also potentially buy items over the phone, without the Internet. Retail items in a store or in a catalog would have a Voice Pay product number as well as a phone number listed that the customer could call. The shopper enters the product number and goes through the process of repeating numbers randomly generated by the computerized attendant.
"I would not rely on it exclusively," said Andreas Stolcke, a senior research engineer at SRI in Menlo Park, CA, and a visiting researcher at the International Computer Science Institute in Berkeley.
Stolcke, whose expertise lies in speech and speaker recognition, said that the way sound is produced in a person's vocal chords and then manipulated by the mouth and tongue is difficult to model. Other variables including the recording channel and background noise add to the difficulty of analyzing the sound and then matching it later.
"It's a little like predicting the weather," said Stolcke. "You can measure the state of the weather at a particular instant and create a model of how it develops from one day to the next, but it's an imprecise model, and you can't always predict what will happen the next day."
But not everyone is as skeptical. Voice Pay's website launched on April 30, 2007 and to date has more than 200,000 people signed up to the use the system once it's adopted by banks. That could be sooner rather than later. Ogden said he's already in discussion with 52 banks around the world, one of which could be yours.