getting a signal level from a signal+noise measure?

[Rochelle Newman <rnewman@xxxxxxxxxxxx>]

Greetings!
I've been searching and asking around, but haven't found any positive
answers, so I thought I'd try here, as well.  Assume one has a
recording of a person talking in the midst of background noise; there
are also portions of the recording where the background noise occurs
without the person talking.  Thus, you have the ability to take
relative measures of the amplitude levels of the signal+noise
combined, and of the noise alone.  (I realize these would not be
absolute amplitude levels, but they'd be accurate relative to one
another.)  Is there a mathematical function by which one can estimate
the amplitude level of the signal alone (and thus determine signal to
noise ratio)?  I realize this would never be exact, but is there a
formula for mathematically subtracting out the dB level of the noise
level and then transforming this in such a way that one can get a
rough estimate of the amplitude level of the signal alone?  (Or, is
there a mathematical function for dB that tells you what level A is
at if you know A+B and B alone?)

Rochelle Newman
--
---------------------------------
Rochelle Newman
Assistant Professor
Dept. of Hearing & Speech Sciences
0100 Lefrak Hall
University of Maryland
College Park, MD 20742

(301) 405-4226 Office (Room 0141BB LeFrak)
(301) 314-2023 FAX
(301) 405-2730 Lab
  http://www.bsos.umd.edu/hesp/newmanr.html