[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Environmental Sound Recognition



Dear Colleagues,

Rich Goldhor and I have been researching the problem of Environmental
Sound Recognition.  We will soon be conducting perceptual experiments
that are motivated by the desire to obtain data to aid us develop a
device for ESR.  The goals are as follows: 1) To develop measures
of similarities of environmental sounds that humans would agree
with, and 2) To develop structured descriptions of environmental
sounds that humans can understand.

We have already referenced the following work:

Bismarck, G.von (1974). "Timbre of steady sounds: A factorial investigation
  of its verbal attributes."  Acustica, 30(3), 146-159.

Bjork, E.A. (1985) "The perceived quality of natural sounds."
  Acustica, 57(3), 185-188.

Bregman, A.S. (1990)  Auditory Scene Analysis.  MIT Press, Cambridge,
  MA.

Brown, G.J. (1992) Computation of Auditory Scene Analysis:
  A Representational Approach.  Ph.D. Thesis .  Department of
  Computer Science, University of Sheffield.

Cooke, M.P. (1991) Modelling Auditory Processing and Organization.
  Ph.D. Thesis .  Department of Computer Science, University of Sheffield.

Deutsch, D. (1982) The Psychology of Music.  Academic Press, Inc.,
  San Diego, CA.

Dorken,E., Milios, E. and Nawab, S.H. (1992) Knowledge-based Signal
  Processing Applications.  In Nawab, H. and Oppenheim, A.V. (eds.)
  Symbolic and Knowledge-based Signal Processing.  Prentice Hall,
  Englewood Cliffs, N.J.

Handel, S. (1993) Listening:  An Introduction to the Perception of
  Auditory Events.  MIT Press, Cambridge, MA.

Voiers, W. D. (1964) "Perceptual basis of speaker identity."
  J. Acoust. Soc. Am., 36(6), 1065-1073.


We would appreciate hearing from anyone who could tell us more
about what's out there.  As usual, we will share the references
we receive with the rest of the mailing list.

The original application is targeted as an assistive-device for the
deaf; wider applications and theoretical work are also under
consideration.  If there is anyone who would be
interested in talking in more depth, please let me know.

Lorin Wilde
wilde@speech.mit.edu