Trayvon Martin, Vigilante Justice

[WildCat]

So, it's good enough for courts of law, but not good enough for you?

Come on now......seriously?

When did a court of law accept into evidence the claim that a scream could be matched to a spoken voice? I must have missed that link, can you post it again?

 

[totoro]

Fact: all of the published papers in this field have made it clear that they need to compare one spoken phrase to another spoken phrase to make the comparison. Preferably the same exact phrase. No published study says they can match a scream to a spoken phrase.

I don't need to be an audio engineering expert to understand they are making an extraordinary claim unsupported by any evidence at all.

Maybe you have some evidence that this can be done? If you post it you'll be the first person in this thread to do so!

Really? You've actually read and understood papers in the field? You know what, I really don't believe this to be the case. I read a bunch last night, following citations from the bibliography in

http://cs.joensuu.fi/pages/tkinnu/webpage/pdf/speaker_recognition_overview.pdf

and not one of them mentioned this "fact". Do you have any citations?

Here's a related snippet from that paper:

"For a given speaker, the supervectors estimated from
different training utterances may not be the same especially when these training samples come from different
handsets. Channel compensation is therefore necessary
to make sure that test data obtained from dierent channel (than that of the training data) can be properly scored
against the speaker models. For channel compensation
to be possible, the channel variability has to be modelled explicitly. The technique of joint factor analysis
(JFA) [110] was proposed for this purpose"

In other words, the problem of the speaker sounding radically different from one sample to another is expected, and the modelling is built around this assumption.

Here is a paper about evaluating different speaker recognition systems in a bakeoff

http://lands.let.kun.nl/literature/leeuwen.2006.2.pdf

This paper does not talk at all about screaming. One issue that may be problematic is the length of the utterance: at least with the systems under test then, they were best off with >60 sec training utterances and > 15 sec test utterances.



As I said, you are just making things up.

 

[Natural Born Skeptic]

Serious science is serious!

Looks like the Trayvon Truthers^TM have found their Gage and Jones!

I just used the technique that the "expert" recommended we try on his youtube video. I looked at it with "my minds eye". Unfortunately just as I was about to see who was screaming a naked woman popped into my minds eye and distracted me. Maybe if I take his long distance course and pass his exam for being a "voice identification expert" he'll teach me how to keep my minds eye properly focused so that doesn't happen.

 

[Kevin_Lowe]

Why yes I can! They claim to be able to match a scream with a spoken voice.

They have provided no evidence at all for this claim. And none of the known published studies on the subject have attempted to do this.

They're the ones claiming to ba able to do this, they must provide the evidence that they can. I won't be holding my breath for them or their apologists to do so.

I asked you if you had any evidence for your arguably-libellous accusations.

None of the above is evidence for your arguably-libellous accusations.

You haven't even managed to respond to the point I put to you earlier, than it seems intuitively obvious that it would be much easier to prove that two voices were different people, than it would be to prove that two voices were definitely the same person.

 

[Chris L]

Do you have any evidence for these accusations at all? So far it seems like those guys are both professionals with relevant credentials and you're a random guy making arguably-libellous accusations on the internet and demanding everyone else do your homework for you.

Exactly. Calling them clowns gives away the game. I don't know any more about this than anyone else on this thread, but I assume that the people who deal with this on a regular basis do. That doesn't mean they are right by a long shot, but it does mean they get the benefit of the doubt. At least until some counter-evidence shows up.

 

[WildCat]

Really? You've actually read and understood papers in the field? You know what, I really don't believe this to be the case. I read a bunch last night, following citations from the bibliography in

http://cs.joensuu.fi/pages/tkinnu/webpage/pdf/speaker_recognition_overview.pdf

and not one of them mentioned this "fact". Do you have any citations?

Here's a related snippet from that paper:

"For a given speaker, the supervectors estimated from
different training utterances may not be the same especially when these training samples come from different
handsets. Channel compensation is therefore necessary
to make sure that test data obtained from dierent channel (than that of the training data) can be properly scored
against the speaker models. For channel compensation
to be possible, the channel variability has to be modelled explicitly. The technique of joint factor analysis
(JFA) [110] was proposed for this purpose"

In other words, the problem of the speaker sounding radically different from one sample to another is expected, and the modelling is built around this assumption.

As I said, you are just making things up. So far, you have displayed zero knowledge of the subject.

You appear to have mistakenly posted something other than support for the claim that a scream could be matched to a spoken voice. I realize this must be embarrasssing for you, but no worry. You can just post the relevant part in your reply to this post!

 

[KatieG]

The hilited part. AGAIN. This is getting silly.

What is the neighborhood watch program and where can I find the rules for the Retreat at Twin Lakes neighborhood watch program?

If one is a member of the neighborhood watch, are you like a police officer, on duty 24x7, or is it possible to act in the capacity of a normal citizen and not a member of the neighborhood watch at any time ?

I can't speak for the Retreat at Twin Lakes but I am a member of our Neighborhood Watch program. The residents of the 10 houses that this encompasses got a 30 minute presentation by the local PD, stickers for our windows and a set of guidelines we were to follow in reporting suspicious activity. Although Oregon is also a SYG state, we were told that under no circumstances should we arm ourselves and confront burglars or other suspicious activity. We are to call 911 and report what we see. Of course, we've been members of this NW for 7 years and haven't ever had to call. We live on possibly the most boring street in the US.

Totally off topic perhaps, but I'm 57 years old and I can count the number of times I've called 911 on one hand. I've lived in a lot of places and in my early years they weren't the best locations. So, if it was 46 calls in 1 year or 10 years, that's a lot of times to call 911 for someone who is 28. IMHO YMMV

Since I don't have to worry about being a juror in this case, I'm more willing to voice an opinion. I'd vote Zimmerman guilty because I can't see any reason for him to grab his gun, get out of his car, and take off after TM. Bringing a gun to a fist fight stretches the limits for me. Equal force and all that.

When I lived in Texas, I learned to handle a gun because I lived in the country and rattlesnakes were so fond of making themselves at home by our front door. I'm a good enough shot to kill a snake but I doubt I could ever raise a gun at another person.

I've read every page of this thread and my head is spinning. Sometimes all the technology in the world won't give you (the generic you) the answers you seek. As much as this case breaks my heart, I doubt we'll see justice done. There are times that just sucks and this will probably be one of those times.

 

[WildCat]

I asked you if you had any evidence for your arguably-libellous accusations.

None of the above is evidence for your arguably-libellous accusations.

You haven't even managed to respond to the point I put to you earlier, than it seems intuitively obvious that it would be much easier to prove that two voices were different people, than it would be to prove that two voices were definitely the same person.

Any evidence at all that a scream van be matched to a spoken voice Kevin? That's what these 2 clowns claim to be able to do. Apparently you can too if you take their long-distance training course!

 

[WildCat]

Exactly. Calling them clowns gives away the game. I don't know any more about this than anyone else on this thread, but I assume that the people who deal with this on a regular basis do. That doesn't mean they are right by a long shot, but it does mean they get the benefit of the doubt. At least until some counter-evidence shows up.

Odd that none of them have ever published a paper showing that a scream can be matched to a voice, isn't it? Or demonstrated such?

 

[triforcharity]

I thought the crux (or one of the cruxes anyway) of the matter was the immunity statute, under which Zimmerman was considered to be immune since he thought he was threatened.

Am I misunderstanding this? I could be, but this is the understanding I've gotten from what I've read about this.

My fundamental problem with such laws is that you can get someone intentionally starting fights and then shooting people when he feels "threatened". In fact, this is something that opponents of such laws have predicted as the outcome of instituting them.

Something pretty similar to that scenario seems to have happened here.

The stand you ground statute means that if someone is attacked in public, they do not need to flee before using deadly force, when they meet force with force. Before, someone was required to run away or avoid the confrontation first, and this law removed that requirement.

There is already a stipulation in the FL SS that says that as the aggressor, you can use deadly force when meeting force with force, but ONLY if you try to break off the altercation before hand. Meaning, the original aggressor would HAVE to, by law, try to run away, or back away from the fight, before they could use deadly force.

So, IF Zimmerman was the aggressor, he would have to meet force with force, and also try to escape or stop the confrontation before using force.

He has no right to stand his ground IF he is the aggressor.

IF he was not, then he would have to have been in fear of his life and meet force with force.

Hope that helps. If you want the actual statutes, let me know, and I will post links.

 

[TheL8Elvis]

I don't know that Twin Lakes had a set of rules.

So therefor, GZ couldn't have broken them. As you claimed.

I don't understand why that was so hard. Just say he appeared to be acting against standard community watch guidelines ... whatever.

I don't understand why you just say you were wrong, or admit you worded it portly, or similar instead of going through all this. Talk about jumping through hoops...

 

[TheL8Elvis]

Are we seriously supposed to believe that any neighborhood watch program recommends chasing after people with a gun because they're walking down the street? Or that any reasonable person would think that doing this is a good idea?

I'm not telling you what to believe or not to believe.

 

[Newtons Bit]

Odd that none of them have ever published a paper showing that a scream can be matched to a voice, isn't it? Or demonstrated such?

I see all kinds of evidence that the software the "expert" used can match a scream to a voice.

 

[Natural Born Skeptic]

I can't speak for the Retreat at Twin Lakes but I am a member of our Neighborhood Watch program. The residents of the 10 houses that this encompasses got a 30 minute presentation by the local PD, stickers for our windows and a set of guidelines we were to follow in reporting suspicious activity. Although Oregon is also a SYG state, we were told that under no circumstances should we arm ourselves and confront burglars or other suspicious activity. We are to call 911 and report what we see. Of course, we've been members of this NW for 7 years and haven't ever had to call. We live on possibly the most boring street in the US.

Totally off topic perhaps, but I'm 57 years old and I can count the number of times I've called 911 on one hand. I've lived in a lot of places and in my early years they weren't the best locations. So, if it was 46 calls in 1 year or 10 years, that's a lot of times to call 911 for someone who is 28. IMHO YMMV

Since I don't have to worry about being a juror in this case, I'm more willing to voice an opinion. I'd vote Zimmerman guilty because I can't see any reason for him to grab his gun, get out of his car, and take off after TM. Bringing a gun to a fist fight stretches the limits for me. Equal force and all that.

When I lived in Texas, I learned to handle a gun because I lived in the country and rattlesnakes were so fond of making themselves at home by our front door. I'm a good enough shot to kill a snake but I doubt I could ever raise a gun at another person.

I've read every page of this thread and my head is spinning. Sometimes all the technology in the world won't give you (the generic you) the answers you seek. As much as this case breaks my heart, I doubt we'll see justice done. There are times that just sucks and this will probably be one of those times.

I think yours is a great post Katie. On a personal level I'm bothered by the idea of an armed citizen following someone, it seems as though that should be reserved for law enforcement officers. But on a legal level, if a state is granting people the right to carry a concealed weapon, then I don't see how anyone can argue (from a legal standpoint) that they can't follow someone they think may be about to commit a crime, just because they have a gun.

I think this is a classic case of how having a gun caused a situation to turn deadly that almost certainly would not have turned deadly, had Zimmerman not had a gun. Instead it would probably have ended with a call to police and an arrest for battery, and both people would have gone home that night.

 

[johnny karate]

So therefor, GZ couldn't have broken them. As you claimed.

I don't understand why that was so hard. Just say he appeared to be acting against standard community watch guidelines ... whatever.

I don't understand why you just say you were wrong, or admit you worded it portly, or similar instead of going through all this. Talk about jumping through hoops...

*sigh*

There exists a standard set of rules for neighborhood watch programs nationwide that indicate members should not pursue suspected criminals or carry guns. I provided a link upthread substantiating this.

Zimmerman broke those rules. Whether he was aware of them or not is irrelevant. He still broke them.

 

[totoro]

You appear to have mistakenly posted something other than support for the claim that a scream could be matched to a spoken voice. I realize this must be embarrasssing for you, but no worry. You can just post the relevant part in your reply to this post!

The point I am making is that nowhere in the literature have I seen it mentioned that yelling/screaming is a huge problem. Different telephones, yes. Yelling, no.

You made a claim that all the papers in the literature mention that screaming is a problem. I called you on this, and asked for some citations. Since you haven't actually read any of the papers, you were incapable of coming up with any citations to back your claim.

So you come back to your Russell's teapot argument. No I have not read any papers that mention classifying screaming text.

At the same time, I have not heard of it being a huge problem, so I'm not willing to say that it is. Speaker variations due to mood or aging are mentioned, but are always mentioned as a distant second to problems with different microphones or telephones.

As I said, you are just making things up. You claimed that all of the papers in the literature mention this as a problem. When confronted with someone who has actually bothered to read a few papers, you went straight for misdirection.

Tendentiousness combined with an argument from ignorance combined with ad hominems combined with just making **** up. That's what you've given us so far.

How about this? You give us any evidence whatsoever that screaming in a test utterance is a major problem for speaker recognition systems. With your deep understanding of the problem, this should be really easy for you, right?

 

[Natural Born Skeptic]

BTW, I keep seeing it repeatedly stated that courts "accept this type of evidence", correct me if I'm wrong on that. But my research is showing me that it's a huge grey. Sometimes courts allow it, sometimes they don't. Here is a statement from the "expert" Thomas Owen himself, who while arguing about how reliable it is states:

The technique of voice identification by means of aural and spectrographic comparison is still an unsettled topic in law

http://www.experts.com/Articles/Voi...-Aural-Spectrographic-Method-By-Thomas-J-Owen

Here is a book on Google that is someone dated (1979) that is nevertheless interesting simply because it gives insight into how the issue has progressed back and forth over the years up to that time.

http://books.google.com/books?id=Fj... on Evaluation of Sound Spectrograms"&f=false

 

[TheL8Elvis]

general questions on voice recognition

Screams aside - isn't one of the questions voice biometrics vs voice spectrography ? It seems voice biometrics is much newer and less proven ? Or am I misunderstanding ?

Also, for all the experience, didn't Mr. Owen just run the voices through his software ? it's all inside the magic software. Two voices go in, a result comes out. So - unless you either a) show me the code or b) show me the studies - can't I be a little suspect that maybe he is trying to sell a product ? And that maybe the lack of a match is a failure of the product ?

Also - does this science trump 2 eyewitnesses + zimmermans claim that he was yelling for help ??

Here is a link to an abstract on the standards of the ABRE:
http://expertpages.com/news/american_board_voice_comparison.htm
This standard specifies recommended practices for the handling, preparation and analysis of recorded evidence to be followed by practitioners of the aural/spectrographic method of speaker identification.
If accurate, does it appear that methodology was followed at all ?

You know what would be interesting and useful .... to see if any recordings the parents must have of TM match the call either. Because if neither match, then you got something interesting.

 

[Unabogie]

I think Wildcat will look back on this episode with considerable embarrassment. The way he's handled this issue is truly beneath him.

I get it. All of the people can see why this is damning and they have a hunch that the experts are going to agree that the scream isn't George Zimmerman. I guess if he ever gets put on trial, he'll have an opportunity to challenge all this. Good.

But this hasn't been a shining moment for some of our veteran members.

 

[RandFan]

I can't speak for the Retreat at Twin Lakes but I am a member of our Neighborhood Watch program. The residents of the 10 houses that this encompasses got a 30 minute presentation by the local PD, stickers for our windows and a set of guidelines we were to follow in reporting suspicious activity. Although Oregon is also a SYG state, we were told that under no circumstances should we arm ourselves and confront burglars or other suspicious activity. We are to call 911 and report what we see. Of course, we've been members of this NW for 7 years and haven't ever had to call. We live on possibly the most boring street in the US.

Totally off topic perhaps, but I'm 57 years old and I can count the number of times I've called 911 on one hand. I've lived in a lot of places and in my early years they weren't the best locations. So, if it was 46 calls in 1 year or 10 years, that's a lot of times to call 911 for someone who is 28. IMHO YMMV

Since I don't have to worry about being a juror in this case, I'm more willing to voice an opinion. I'd vote Zimmerman guilty because I can't see any reason for him to grab his gun, get out of his car, and take off after TM. Bringing a gun to a fist fight stretches the limits for me. Equal force and all that.

When I lived in Texas, I learned to handle a gun because I lived in the country and rattlesnakes were so fond of making themselves at home by our front door. I'm a good enough shot to kill a snake but I doubt I could ever raise a gun at another person.

I've read every page of this thread and my head is spinning. Sometimes all the technology in the world won't give you (the generic you) the answers you seek. As much as this case breaks my heart, I doubt we'll see justice done. There are times that just sucks and this will probably be one of those times.

Thanks. Good post.