Slashdot Mirror
Forensic Experts Say Screams Were Not Zimmerman's
Hugh Pickens writes "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? Now the Orlando Sentinel reports that Tom Owen, a leading expert in the field of forensic voice identification sought to answer that question by analyzing the recordings. His result: It was not George Zimmerman who called for help. 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. Owen 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,' says Owen. The software compared that audio to Zimmerman's voice and returned a 48 percent match. Owen says to reach a positive match with audio of this quality, he'd expect higher than 90 percent. Owen cannot confirm the voice as Trayvon's, because he didn't have a sample of the teen's voice to compare however 'you can say with reasonable scientific certainty that it's not Zimmerman.'"
Has this software been subjected to repeated double-blind testing? Otherwise, there's no point in reporting this.
I think there's a significant problem in the way this software is being used in this case. It is one thing to say that, based on samples of an individual's voice, that there is X probability that some other voice sample could be from the same person. However, there isn't any way the software can do the opposite and prove a negative. For example, you can take hours of recordings of my voice from phone conversations and train the software. Now, if I make my voice sound like Donald Duck, or if I sing in falsetto, which are two types of sounds that would not be in the sampling of my normal voice, what probability would the software return that the silly voice matches my normal voice? It would be very low, at is should be.
In this case we have a sample of someone's NOT NORMAL VOICE. They are screaming and yelling. What voice samples of Zimmerman's were used to train the software? Was it recordings of him screaming and yelling? If not then of course the software will return a low probability. Actually, I'm surprised it returned as high of a probability as it did.
Now, as a side note, I think the news is really trying to inflame this whole deal. I think Zimmerman is likely in the wrong here, however, the media is running rampant with speculation. A good example are the video clips of Zimmerman at the police station, and them (news media) saying it doesn't look like his nose is broken, or that there doesn't appear to be blood all over him. That sort of thing is completely impossible to determine from the crappy, low resolution security video. Again, yes, if there was that much blood and it could be seen in the video, then a positive could be "proven", but just because it doesn't show up in the video doesn't mean he has significant injuries or a broken nose, etc.
Better known as 318230.
This reminds me of the infamous plane identification software. Its accuracy got up to 100%. They were so happy that they managed to do it. Put it out in the field and there were all sorts of false positives and false negatives. Turns out that the software got so good at guessing because with the test photos, all the good planes were shot against bright blue sky and the bad planes were shot against dark sky. The software made all its predictions based on the sky color.
Voice analysis is a well established and studied technique. Unless you're particularly practiced and adept at disguising your voice, there are certain characteristics introduced by the physics of your vocal cords, throat, mouth, and nasal passages that are pretty consistent and identifiable, even with most people doing "impersonations" that sound like some other person. So, yes, it's reasonable to rule out that it was Zimmerman, in fact, it's more reliable at excluding people than at matching them. As Mr Owen points out, this recording has low background noise levels, and it's got a notable amount of Zimmerman's speech recorded in addition to the screams for help, so there is no issue introduced by aging, colds, etc. It's a nearly ideal case for matching.
make imaginary.friends COUNT=100 VISIBLE=false
Having seen the full video, I can come to only one conclusion: the video does not show any solid evidence of injuries because the quality is low. I saw some things that may have been injuries, but they could have just as easily been due to the shape of his head.
By the way, Sanford has put up the videos and 911 calls at http://sanfordfl.gov/investigation/trayvon_martin.html
Fuck Beta
After the Richard Jewel case I don't get into rush to judgement any more.
However the initial response of the police to let Zimmerman walk without a real investigation deserves a whole lot of criticism. Now we are getting the investigation so hopefully the facts will become evident.
Note that the video was taken well *after* EMTs had treated him at the scene. I wouldn't expect video of that quality to show anything at that point. While it would be interesting to hear what the EMTs saw, if they say he appeared to have been beaten you won't believe them.
Interesting thing about the video is that the original source looks like it was recorded on videotape as interlaced NTSC! You can see this when there's a great deal of movement going on. Just look for areas of great contrast like the hood of the police car when it rolls in and you'll notice the odd saw-tooth appearance of the hood's edge. This happens in other places.
What this means is that a lot of what is being seen is what has been filled in by software as it deals with crappy NTSC. Noise, color fringing effects, are all smoothed out. Then lossy compression is used during the conversion to digital video and potentiall important detail is lost.
The result is that the video appears better than it really is.
This is what most people want when they're transferring analog video to digital. But here is it's absolutely essential that we see the raw, unaltered video, if for no other reason than for understanding the limits of equipment used. It possible the equipment just wasn't good enough to pick up the details we're looking for.
The weird thing I don't get about the "stand your ground" law in this case is how it can apply to both people. By his own account, Zimmerman was chasing Martin. Zimmerman was armed with a gun and was not in a marked security vehicle or wearing any sort of uniform, nor did he identify himself in any way as being part of the neighborhood watch. If Zimmerman had never shot Martin, but Martin had been arrested for attacking Zimmerman (and I'm not saying that's what happened, I'm just looking at Zimmerman's claimed version of events), then "stand your ground" should have been a viable defense for him. He was the one in fear for his life being chased by a suspicious stranger armed with a gun.
Everything that's been revealed about Zimmerman seems to show that he's basically a hyper-aggressive Gladys Kravitz with a gun. In the past he'd called 911 to report suspicious 7-9 year old black males, kids playing in the street, and, apparently, his landlord demanding the rent money. He forced this situation and someone else ended up dead. He's clearly at least guilty of manslaughter.
I'm undecided on wether Zimmerman is guilty or not without seeing further evidence myself. But it would be a stretch to call Trayvon "muscular". Kid weighed 140 pounds at 6' 3". I weigh that at 5' 7" and people think I'm too thin. He was a beanpole.
Happy people make bad consumers.
It's always bothered me that forensic science doesn't involve science. It would be easy enough to reproduce the events using the same phone and recording equipment and voice samples with a few different people to establish a baseline for what we "should" expect. But instead they simply can't be bothered with scientific controls. We are just supposed to take their word for it that it should be a "90%" match. I'm this context we don't even know what 90% means.
If "Stand your ground" means, that you can use deadly force against someone you feel threatened by if you are on your own hometurf, and Mr. Zimmerman can rightfully claim this, then how comes, Mr. Martin should not have the right to confront someone he feels threatened by with deadly force?
If Mr. Zimmerman had this right, then Mr. Martin had it more, because his fears were obviously justified.
In 2009 there were 2,867 black males killed in the United States, of which 2,604 were killed by other blacks, 209 killed by whites. Why the outrage in this case? Might it be various people made assumptions about how this would play out?
It might, might, might just have something to do with the fact that this was not such a cut and dry scenario, and the suspect wasn't arrested. Of those 2,867 killings you cite, how many of those killers were arrested for murder or manslaughter? How many of those cases were regarded as self-defense?
People are understandably quick to bring race into the equation, but on it's most underlying level, an unarmed boy was shot by a large adult with a gun and an arrest wasn't made. The unarmed boy was reportedly making a run for junk food for his younger brother, the armed man was at some point following the boy around after being advised not to because the police were on the way. It's suspicious, regardless of what color either character is.