(320) previous ~ index ~ next
To: TDT Distrib <firstname.lastname@example.org>
From: Jonathan Fiscus <email@example.com>
Subject: [Fwd: ACM SIGIR Workshop on IR Techniques for Speech Applications, New
Date: Thu, 10 May 2001 13:59:01 -0400
ACM SIGIR'01 Workshop on
Information Retrieval Techniques for Speech Applications
New Orleans, Louisiana, September 13, 2001
CALL FOR PAPERS
In the last few years automatic speech recognition has left the confines
the basic research lab and become a viable commercial application.
recognition technology has now matured to the point where speech can
used to interact with automated phone systems, control computer
and even create memos and documents. Moving beyond computer control
dictation, speech recognition has the potential to dramatically change
way we create, capture, and store knowledge. Advances in
recognition technology combined with ever decreasing storage costs
processors that double in power every eighteen months have set the
for a whole new era of applications that treat speech in the same way
we currently treat text. The goal of this workshop is to explore
technical issues involved in applying information retrieval and
analysis technologies in the new application domains enabled by
These possibilities bring with them a number of issues, questions,
problems. Speech-based user interfaces create different expectations
the end user, which in turn places different demands on the
systems that must interact with the user and interpret the user's
Speech recognition will never be perfect, so analyses applied to
resulting transcripts must be robust in the face of recognition
The ability to capture speech and apply speech recognition on smaller,
powerful, pervasive devices suggests that text analysis and
technologies can be applied in new domains never before considered.
About the Workshop
In this workshop we would like to explore techniques in
retrieval and text analysis that meet the challenges in the new
domains enabled by automatic speech recognition.
Specifically, we would like to focus on:
1. What new IR related applications, problems, or opportunities are
created by effective, real-time speech recognition?
2. To what extent are information retrieval methods that work on
text applicable to imperfect speech transcript?
3. What additional data representations from a speech engine may be
exploited by applications?
4. Does domain knowledge (context/voice-id) help and can it be
5. Can some of the techniques explored be beneficial in a standard IR
6. What constraints are imposed by real time speech applications?
7. Case studies of specific speech applications - either successful or
The workshop will include a keynote address by James Allan
Amherst), presentations of accepted papers, and demos of
prototypes. The accepted papers will be published on the WWW and bound
a workshop proceedings distributed to the workshop attendees.
Anni Coden, IBM T.J. Watson Research Center
Savitha Srinivasan, IBM Almaden Research Center
Eric Brown, IBM T.J. Watson Research Center
John Garofolo, NIST
Alex Hauptmann, CMU
Alan Smeaton, Dublin City University
Justin Zobel, RMIT Australia
James Allan, UMass at Amherst
Please submit a 3-5 page paper and, if appropriate, a one page
of a working prototype to be shown. Email submissions in PostScript or
to Anni Coden, firstname.lastname@example.org. We are looking for papers
recent or preliminary work.
IBM T.J. Watson Research Center
P.O. Box 704
Yorktown Heights, NY 10598
Phone: +1-914-784-7073, Fax: +1-914-784-6307
Submission deadline: June 18, 2001
Acceptance: July 16, 2001
Final Versions: July 30, 2001
Further Information can be found on the SIGIR 2001 Web pages
(320) previous ~ index ~ next
Last updated Wed Aug 22 16:07:32 2001