On Thu, Oct 17, 2013 at 6:41 AM, GtwoG PublicOhOne <g2g-public01(a)att.net>wrote;wrote:
And voiceprint attribution was 99.96% accurate as of
(published); fast-forward at the speed of Moore's law, draw your own
conclusions, and more details in person.
Note that the accuracy of voiceprint identification has been hugely
exaggerated. That number has been touted primarily by prosecutors, and by
voiceprint identification "experts" who make a nice buck from offering
their services. But just as has been the case with lie detectors, these
claims have not stood up to rigorous scientific validation.
Of course, that doesn't mean that they won't be used against you in a court
of law, regardless of your guilt or innocence! And some
been falsely convicted to decades in jail or worse on the basis of
this kind of "evidence".
Forensic speaker recognition has many limitations and is currently
inadmissible in federal court as expert testimony. Bonastre et al (2003)
summarize these limitations quite well:
"The term *voiceprint* gives the false impression that voice has
characteristics that are as unique and reliable as fingerprints... this is
absolutely not the case."
The thing about voices is that they are susceptible to a myriad of external
factors such as psychological/emotional state, age, health, weather... the
list goes on. From an application standpoint, the most prominent of these
factors is intentional vocal disguise. There are a number of things people
can intentionally do to their voices to drastically reduce the ability of
machine or human expert to identify their voice correctly (you would be
amazed at how difficult it is - nearly impossible - to identify a whispered
voice). Under these conditions, identification accuracy falls to 40 - 52
percent (Thompson 1987), 36 percent (Andruski 2007), 26 percent (Clifford