[Discuss] Fidelity voice-recognition security?

[rlk at alum.mit.edu (Robert Krawitz)]

On Wed, 22 Nov 2017 13:15:33 -0500, Joe Polcari wrote:
> As already mentioned - my voice can be recorded. Not secure at all.

Not to mention that I don't know that I'd really want to trust that
voices are that unique, especially with so much of the high frequency
cut off.

And voices do change, both short and long term.  What happens with
voice ID when you have a respiratory infection, blocked sinuses, what
have you?

> On 11/22/17, 12:17 PM, "Discuss on behalf of Richard Pieri"
> <discuss-bounces+joe=polcari.com at blu.org on behalf of
> richard.pieri at gmail.com> wrote:
>
>>On 11/21/2017 11:27 AM, Daniel Barrett wrote:
>>> I declined the feature. Fingerprinting a voice uniquely over a
>>> low-quality telephone line? I can't imagine that's more secure than a
>>> non-obvious password. What does the security crowd here think?
>>
>>Passwords suck. Voices are unique. In principle, voice identification
>>can be a good authentication system. In practice, it depends on how many
>>retries and how much deviation from a given user's baseline the system
>>permits.

-- 
Robert Krawitz                                     <rlk at alum.mit.edu>

***  MIT Engineers   A Proud Tradition   http://mitathletics.com  ***
Member of the League for Programming Freedom  --  http://ProgFree.org
Project lead for Gutenprint   --    http://gimp-print.sourceforge.net

"Linux doesn't dictate how I work, I dictate how Linux works."
--Eric Crampton