[Dave Birch] We’ve discussed the importance of voice biometrics in the digital identity world before, and it’s clear that they will change quite a few businesses once they work properly (ie, not perfectly, but with the right balance of false accept and false reject rates). Payments, for example. If you could pay for things by just talking into your mobile phone that would be pretty good. And friendly, and easy.

Technorati Tags:

If we’re serious about bringing digital identity to the mass market, then the mobile phone in the natural platform. For one thing, there are now three billion mobile phone subscriptions although, as Tomi points out, that does not mean the world has 3 billion mobile phone owners because one in four mobile phone owners has two or more subscriptions. Even in the U.S., the multiple subscription rate is already 15%. What all this means is that according to Informa the total mobile phone user base is 2.3 billion (up from 2.1 billion at the start of year). China Mobile added more than five million subscribers last month.

For another thing, the phone has all of the components needed to implement a 21st century vision of an identity card rather than simulate the 1950s cardboard version. This new vision is more about a utility than it is about a product or a service or a technology, and it contains the potential to make a real change for the better in day-to-day living because cryptography can deliver (apparently paradoxically) both more security and more privacy. This is the kind of thing that I’ll be talking about at the Mobile Monday London event on Mobile Digital Identity on Monday 6th August. See you there.

These opinions are my own (I think) and are presented solely in my capacity as an interested member of the general public [posted with ecto]

2 comments

  1. Re: “but with the right balance of false accept and false reject rates”
    Actually, error rates with Voice Biometrics are surprisingly low. You can check Dr. Clive Summerfield’s evaluation reports for more on this (linked from http://www.spokenproof.com/news/2007/7/16/scientific-evaluation-of-speaker-verification-technologies ).
    Also, working on a case study of AHM’s deployment of Voice Biometrics (that I’m expect to complete next week and post to http://www.SpokenProof.com ) I came across even better error rates than reported by Dr. Summerfield. In their system they have seen no false accepts (that they know of anyway) and less than 1% false rejects. I’d say these are quite remarkable. These great stats are also attributable to some smart choices they made in their processes.

Leave a Reply


Subscribe to our newsletter

You have successfully subscribed to the newsletter

There was an error while trying to send your request. Please try again.

By accepting the Terms, you consent to Consult Hyperion communicating with you regarding our events, reports and services through our regular newsletter. You can unsubscribe anytime through our newsletters or by emailing us.
%d bloggers like this: