Question about source separation

great....my email-address is donniebrasco9 AT hotmail.com

thanks..
--------

"naebad" <minnaebad@yahoo.co.uk> skrev i en meddelelse 
news:1131650230.976145.309610@g49g2000cwa.googlegroups.com...
> Hi,
>
> I am sorry that I am not an ICA person but i have seen a demo where C1
> and C2 are constants and it  worked perfectly using ICA. If you leave
> your email I will put you in touch with the Prof that did this.
> Different story when C1 and C2 were time-varying z-transfer functions
> though. My own experience is with beamforming and I get about 12 dB
> reduction in 'noise' (noise being the unwanted speech) using 2 mics in
> a real reverberent environment. I am publishing this next year at a
> conference. I cannot separate the two but I am only interested in the
> signal - not the 'noise'. The only time when you might consider C1 and
> C2 to be constants are when you are in an anechoic chamber - and even
> then they would be pure delays. In a reverberant environment they would
> be non-min phase transfer functions + pure time-delays.
>
> Naebad
> 

Hi again...

You do realize that I am looking for an algorithm that can extract an 
estimate of the 2 unknown sources based on _only_ 1 observation ??

Thanks...

------------------
>using 2 mics in
> a real reverberent environment. I am publishing this next year at a

Hi, I said in an earlier post on this thread that if you have only one
sensor then forget it! There have been attempts at this but I would not
hold out much hope.

Naebad

> Hi, I said in an earlier post on this thread that if you have
> only one sensor then forget it!

He did say that the two signals are correlated, ie. you have

Y(t)=a*S1(t)+b*S2(t),

where S1 and S2 are correlated. For example, if S1 = f(S2), with f
injective, then I think one can give a pretty good estimate on S1 given
only Y. The quality of the estimation depends on how strongly the two
signals are correlated.

Regards,
Andor

so how do I solve that problem? Any litterature I should read? It would be 
great with a matlab script that solves this particular kind of problem...


----------
> only Y. The quality of the estimation depends on how strongly the two
> signals are correlated.
>
> Regards,
> Andor
> 

"Lars Hansen" <jojo@yahpoo.com> wrote in message
news:43747a50$0$78280$157c6196@dreader1.cybercity.dk...
> so how do I solve that problem? Any litterature I should read? It would be
> great with a matlab script that solves this particular kind of problem...
>
>
> ----------
> > only Y. The quality of the estimation depends on how strongly the two
> > signals are correlated.
> >
> > Regards,
> > Andor
> >
>
>
I doubt you will be able to solve this.

McC