A couple of the leading experts in the field of forensic voice identification have answered one of the many questions surrounding the Trayvon Martin shooting. Who was it exactly heard screaming for help on the 911 call recording.
Tom Owen, forensic consultant for Owen Forensic Services LLC and chair emeritus for the American Board of Recorded Evidence, used voice identification software to come to the conclusion that it was not Zimmerman screaming for help. Another expert, also contacted by the Orlando Sentinel, utilizing different techniques, came up with the same results.
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 and record the panicked cries and the gunshot that took Trayvon Martin’s life.
Zimmerman claims self-defense in the shooting death of Martin and told police he was the one 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, which came back a 48 percent match. In order to obtain a positive match results would have to be higher than 90 percent.
“As a result of that, you can say with reasonable scientific certainty that it’s not Zimmerman,” said Owen, but he cannot confirm the voice as Trayvon’s because he didn’t have a sample of the teen’s voice to compare.
The technology Owen used to analyze the recording has been utilized for national security and international policing, he said. In January, Owen used the same technology to identify accused murderer Sheila Davalloo in a 911 call made almost a decade ago.
Davalloo was accused of stabbing another woman nine times in a condo in Shippan, Conn.
She was convicted.
Owen says the quality of the audio in the Zimmerman case is much better than the 911 call in the Davalloo case. Voice identification experts judge the quality based on a signal-to-noise ratio, comparing the usable audio in a clip to the environmental noises that make a match difficult.
“In our world, that’s the home run,” he says.
Ed Primeau, a Michigan-based audio engineer and forensics expert, is not a believer in the technology’s use in courtroom settings.
He relies instead on audio enhancement and human analysis based on forensic experience. After listening closely to the 911 tape on which the screams are heard, Primeau came to the same conclusion as Owen.
“I believe that’s Trayvon Martin in the background, without a doubt,” Primeau says, stressing that the tone of the voice is a giveaway. “That’s a young man screaming.”