5th ISCA Speech Synthesis Research Workshop
http://www.ssw5.org
Carnegie Mellon University
Pittsburgh, USA
June 14-16th 2004
SUBMISSION DEADLINE EXTENSION
The deadline for paper submission has been extended.
Full papers (6 pages) in pdf are due 10th March. And a new "NOTE"
category which encourages presentation of latest results has been
introduced. Notes should be 2 pages in length, and if accepted, will be
presented at a special poster session at the workshop.
This is a call for papers for a research workshop on new issues in
speech synthesis. We welcome papers on all aspects of speech synthesis
and generation including but not limited to:
prosody
signal processing
voice building
emotional and stylistic speech
text processing for audio output
unit selection
multimodal synthesis
articulatory synthesis
concept-to-speech
voice transformation
evaluation
Presentations will be oral, poster and panel sessions with keynote
speeches from invited speakers. Demonstration, both commercial and
academic are strongly encouraged.
Following in the line of previous speech synthesis workshops, in
Autrans 1990, Mohonk 1994, Jenolan Caves 1998 and Pitlochry 2001, we
are encouraging new people and hence have arranged the workshop at an
accessible University campus.
Location
In order to provide suitable accommodations for oral sessions,
posters, panels and demonstrations we have chosen to run the workshop
on a University campus that can economically provide a suitable
infrastructure. Following previous such workshops most meals will be
provided so that the sense of community may be fostered. Dorm rooms
will be available as well as rooms at local hotels. The conference
itself will be held in the University Center in the center of CMU's
campus. Carnegie Mellon has a long history in computation and
particularly in speech technology, besides CMU is in Pittsburgh, the
city with TTS at its heart.
Important Dates
10th Mar 2004: Full Paper Submission (6 pages)
17th Mar 2004: Notes Submission (2 pages)
22nd Apr 2004: Paper acceptance/rejection notices
22nd Apr 2004: Registration begins
8th May 2004: Revised papers due
14-16th Jun 2004: Workshop
Scientific Committee
Kevin Lenzo, CTO, Cepstral LLC and Carnegie Mellon (General Chair)
Alan W Black, Carnegie Mellon and Cepstral, LLC (Program Chair)
Gerard Bailly, CNRS-STIC, France.
Nick Campbell, ATR, Japan.
Rolf Carlson, KTH, Sweden.
Min Chu, Microsoft Research Asia, China.
Wolfgang Hess, Unversity of Bonn, Germany.
Bernd Mius, University of Stuttgart, Germany.
Jan van Santen, Oregon Health & Science University, USA.
Richard Sproat, University of Illinois at Urbana-Champaign, USA.
Paul Taylor, Rhetorical Systems, UK.
Keiichi Tokuda, Nagoya Institute of Technology, Japan.
Special Sessions
Common Synthesis Resources
Following the release of CMU_ARCTIC (http://festvox.org/cmu_arctic/) 4
signal speaker speech phonetically balanced speech databases. We
encourage submissions based on this commonly available data.
Alan W Black email: XXXX@XXXXX.COM
Language Technologies Institute http://www.cs.cmu.edu/~awb/
Carnegie Mellon University tel: +1-412-268-6299
5000 Forbes Ave, Pittsburgh PA, 15213, USA. fax: +1-412-268-6298