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

[CFP] IJCAI-95 Workshop on CASA (was: Sheffield Meeting)

Dear colleagues,

> We will circulate abstracts but there won't be any proper proceedings. The
> meeting was originally intended primarily for the UK community, but it's
> clear that we have struck a rich vein. Perhaps there should be some kind of
> follow-up, or a more formal occasion with proceedings. What do people think?
> - responses to me & I will summarise. There is the proposed Computational
> ASA workshop at IJCAI-95 to look forward to of course.

Yes, the proposal of IJCAI-95 Workshop on Computational Auditory Scene
Analysis is accepted.  Enclosed is a copy of CFP.
CFP of postscript version is placed at

        sail.stanford.edu: ~ftp/pub/casa/ijcai95-casa-cfp.ps

Please post and/or redistribute it to whom it may concern.

I hope many people will submit a paper or attend the workshop.


Hiroshi G. Okuno
NTT Basic Research Laboratories

                         Call For Papers

                     IJCAI-95 Workshop on
               Computational Auditory Scene Analysis

                 August 19-20, 1995, Montreal, CANADA
                       Two day workshop

The interest of AI in problems related to understanding sounds has a
rich history dating back to the ARPA Speech Understanding Project in
the 1970's.  While a great deal has been learned from this and
subsequent speech understanding research, the goal of building systems
that can understand general acoustic signals (e.g. continuous speech
and/or non-speech sounds) from unconstrained environments is still
unrealized.  Instead, there are now systems that understand "clean"
speech well in relatively noiseless laboratory environments, but that
break down in more realistic, noisier environments.  As seen in the
"cocktail-party effect," humans (and other mammals) have the ability
to selectively attend to sound from a particular source, even when it
is mixed with other sounds.  Computers also need to be able to decide
which parts of a mixed acoustic signal are relevant to a particular
purpose -- which part should be interpreted as speech, for example,
and which should be interpreted as a door closing, an air conditioner
humming, or another person interrupting.

Observations such as these have led a number of researchers to
conclude that research on speech understanding and on non-speech
understanding need to be united within a more general framework.  One
such framework is suggested by the Bregman's recent book, "Auditory
Scene Analysis" (MIT Press, '90).  This work has inspired a number of
systems that attempt to model what is known about the human auditory
system.  It has also encouraged researchers to explore general models
of the structure of sounds in order to deal with more realistic
acoustic environments.  Researchers have also begun trying to
understand computational auditory frameworks as parts of larger
perception systems whose purpose is to give a computer integrated
information about the real world.  Inspiration for this work ranges
from research on how different sensors can be integrated to models of
how humans' auditory apparatus works in concert with vision,
proprioception, etc.

This workshop will provide a forum for researchers to compare
approaches to AI-oriented auditory scene analysis.  We invite papers
from researchers active in all fields which have a bearing on this
complex and diverse field.  The topics include, but are not limited to:

- Modeling Issues:
        Cognitive Modeling
        Low-level Auditory Models
        Evaluation of Auditory models from viewpoint of engineering

- Sound Understanding:
        Auditory Stream Segregation
        Multi-Modal Understanding (i.e. integration with other perceptual
        Engineering Aspects of Psychoacoustics

-Architectural Issues:
        Unified Architectures
        Blackboard Architectures
        Multi-Agent Paradigm
        Hybrid Approach to Top-Down/ Bottom-Up processing

- Control Issues:
        Reactive/ Planned Behavior
        Adaptive Behavior

- Representational Issues:
        Representation of Audition
        Representation of Speech
        Representation of Music
        Unified Representation of (possibly Dynamic) Vision and Audition

- Applications:
        Speech Understanding
        Music Understanding
        Multi-Modal Integration


Please submit a detailed abstract (approx. 1500 words) or a full paper
(limited to 5000 words) by February 20.  For those who can submit
electronically, please submit materials in plain, unformatted text or
Postscript text to casa-submission@mit.media.edu.  For those who can
not submit via e-mail, send five hard copies to David Rosenthal to
arrive by February 20, 1995.  All submitted papers will be reviewed by the
workshop committee.

Time table:

Papers due:                   February 20, 1995
Notification of Acceptance:   March 15, 1995
Camera-ready copy due:        April 20, 1995

Important Notice

Delegates should note that workshop participation is not possible
WITHOUT REGISTRATION for the main conference (International Joint
Conference on Artificial Intelligence, IJCAI-95).

Workshop Committee

David Rosenthal (co-chair)
16 Surrey Road
Woburn, MA 01801
Phone (617) 935-3644

Hiroshi G.  Okuno (co-chair)
NTT Basic Research Laboratories
3-1 Morinosato-Wakamiya, Atsugi
Kanagawa, 243-01 Japan

Malcolm Crawford
University of Sheffield, UK

S. Hamid Nawab
Boston University, USA

Malcolm Slaney
Interval Research, Inc.  USA

Call For Papers of Postscript version is available by anonymous FTP.

        sail.stanford.edu: ~ftp/pub/casa/ijcai95-casa-cfp.ps