From the Orlando Sentinel:

Trayvon Martin shooting: It's not George Zimmerman crying for help on
911 recording, 2 experts say
5:38 p.m. EST, March 31, 2012|

By Jeff Weiner, Orlando Sentinel



As the Trayvon Martin controversy splinters into a debate about
self-defense, a central question remains: Who was heard crying for help
on a 911 call in the moments before the teen was shot?

A leading expert in the field of forensic voice identification sought to
answer that question by analyzing the recordings for the Orlando Sentinel.

His result: It was not George Zimmerman who called for help.

Tom Owen, forensic consultant for Owen Forensic Services LLC and chair
emeritus for the American Board of Recorded Evidence, used voice
identification software to rule out Zimmerman. Another expert contacted
by the Sentinel, utilizing different techniques, came to the same
conclusion.

Zimmerman claims self-defense in the shooting and told police he was the
one screaming for help. But these experts say the evidence tells a
different story.

'Scientific certainty'

On a rainy night in late February, a woman called 911 to report someone
crying out for help in her gated Sanford community, Retreat at Twin Lakes.

Though several of her neighbors eventually called authorities, she
phoned early enough for dispatchers to hear the panicked cries and the
gunshot that took Trayvon Martin's life.

George Zimmerman, a Neighborhood Watch volunteer, shot Trayvon, an
unarmed 17-year-old, during a one-on-one confrontation Feb. 26.

Before the shot, one of them can be heard screaming for help.

Owen, a court-qualified expert witness and former chief engineer for the
New York Public Library's Rodgers and Hammerstein Archives of Recorded
Sound, is an authority on biometric voice analysis — a computerized
process comparing attributes of voices to determine whether they match.

After the Sentinel contacted Owen, he used software called Easy Voice
Biometrics to compare Zimmerman's voice to the 911 call screams.

"I took all of the screams and put those together, and cut out
everything else," Owen says.

The software compared that audio to Zimmerman's voice. It returned a 48
percent match. Owen said to reach a positive match with audio of this
quality, he'd expect higher than 90 percent.

"As a result of that, you can say with reasonable scientific certainty
that it's not Zimmerman," Owen says, stressing that he cannot confirm
the voice as Trayvon's, because he didn't have a sample of the teen's
voice to compare.

Forensic voice identification is not a new or novel concept; in fact, a
recent U.S. Department of Justice committee report notes that federal
interest in the technology "has a history of nearly 70 years."

In the post 9-11 world, Owen says, voice identification is "the main
biometric tool" used to track international criminals, as well as
terrorists.

"These people don't leave fingerprints, but they do still need to talk
to one another," he says.