| | ODYSSEY 2014: THE SPEAKER AND LANGUAGE RECOGNITION WORKSHOP
June 16-19, 2014, Joensuu, Finland
http://cs.uef.fi/odyssey2014/
https://www.facebook.com/SpeakerOdyssey2014
Registration now opened:
http://cs.uef.fi/odyssey2014/registration/
Early-bird deadline: April 30
Late-bird deadline: May 31
------------------------------------------------------------------------
KEYNOTE TALKERS:
Dr. Samy Bengio, Google Research
http://research.google.com/pubs/bengio.html
'Large scale learning of a joint embedding space'
Prof. Martin Cooke, University of the Basque Country
http://laslab.org/martin
'Speaking in adverse conditions: from behavioural observations to
intelligibility-enhancing speech modifications'
Dr. Joseph P. Campbell, MIT Lincoln Lab
http://www.ll.mit.edu/mission/cybersec/HLT/biographies/campbell-bio.html
'Speaker Recognition for Forensic Applications'
------------------------------------------------------------------------
CONFERENCE TOPICS:
The general themes of the conference include speaker and
language recognition and characterization. The specific topics
include, but are not limited to, the following:
o Speaker characterization and adaptation
o Features for speaker and language recognition
o Multi-speaker training, detection and diarization
o Robustness in channels and environment
o Robust classification and fusion
o Speaker recognition corpora and evaluation
o Speaker recognition with speech recognition
o Forensics, multimodality, and multimedia speaker recognition
o Speaker and language confidence estimation
o Language, dialect, and accent recognition
o Speaker synthesis and transformation
o Human recognition of speaker and language
o Analysis and countermeasures against spoofing attacks
o Commercial applications
------------------------------------------------------------------------
REGULAR PAPER SUBMISSIONS:
All regular submissions (max 8 pages) will be reviewed by at least
three members of the scientific review committee. The regular
submissions must include scientific or methodological novelty; the
paper has to review the relevant prior work and state clearly the
novelty in the Introduction part. The accepted papers will appear in
electronic proceedings.
------------------------------------------------------------------------
INDUSTRY TRACK AND DEMOS:
Odyssey committee recognizes a large gap between theoretical research
results and real-world deployment of the methods. To foster closer
collaboration across industry and academia, Odyssey 2014 features an
industry submission track. This can include a description of your
target application, a product, a demonstrator, or any combination. In
addition to voice biometrics providers, we encourage submissions from
companies who are in need for speaker or language recognition
technology. The industry paper submissions do NOT have to present
methodological novelty, but the submission MUST address one or all of
the following aspects:
- Description of the application, role of speaker/language recognition
- Research results and methods that worked well in your application
- Negative research results that have NOT worked in practice
- Unsolved problems 'out-in-the-wild' that deserve attention
The industry submissions will NOT undergo full peer review
nor will be included to the proceedings. All the industry track
submissions can be presented as a posters. The organizing committee
may select a few most interesting ones for oral presentation.
------------------------------------------------------------------------
NIST SPECIAL SESSIONS: I-VECTOR CHALLENGE & NIST SRE-2012 FOLLOW-UP
In addition to regular and industry paper submissions, Odyssey 2014
features two special sessions co-organized with National Institute of
Standards and Technologies (NIST). NIST SRE-2012 special session
focuses on extended analyses on the latest, NIST 2012 speaker
recognition evaluation (SRE) benchmark, and is targeted for the
participants of NIST SRE 2012.
The i-vector challenge is a new type of challenge targeted for anyone
interested for a 'quick start-up' in speaker recognition. Building
modern speaker and language recognition systems requires a lot of
preprocessing, corpus engineering and computations, making it
challenging for newcomers to enter the field. This prohibits piloting
of possibly promising modeling ideas developed outside of speaker
recognition community (e.g. machine learning and image processing
communities). To bridge this gap, NIST organizes a new type of
benchmark, i-vector challenge, synchronized with Odyssey 2014.
Preliminary due-date for paper submissions to both special sessions is
February 2014. Submissions by this deadline will undergo review both
by NIST and by the scientific review committee, and will be included
to the conference proceedings if accepted. Late challenge submissions
(without a paper) are also encouraged; they can be presented as
posters, but will not undergo peer review nor will be included to the
conference proceedings.
To ensure smooth organization, early (non-binding) preliminary sign-up
is required. More details and registration for the i-vector challenge
will be available in November 2013.
See https://ivectorchallenge.nist.gov/ for more info about the i-vector
challenge.
------------------------------------------------------------------------
AWARDS:
Odyssey 2014 features three awards:
- A best paper award
- A best student paper award
- Free registration for 1 to 2 top-performers in the i-vector challenge
All regular and special session papers submitted in time are
candidates for the awards. The awards are given based on the review
reports AND the presentation at the conference. For the best student
paper award, the first author must be a student (does not yet hold a
PhD degree) at the time of paper submission.
Best 1 to 2 teams (max 1 person per site) in i-vector challenge are
provided FREE REGISTRATION to the full Odyssey 2014 workshop.
------------------------------------------------------------------------
ORGANIZING COMMITTEE:
Tomi Kinnunen, chair University of Eastern Finland, Finland
Pasi Franti, co-chair University of Eastern Finland, Finland
Jean-Francois Bonastre University of Avignon, France
Niko Brummer Agnitio, South Africa
Lukas Burget Brno Univ. Technology, Czech Republic
Joseph Campbell MIT Lincoln Lab, USA
Jan 'Honza' Cernocky Brno Univ. Technology, Czech Republic
Haizhou Li Inst. Infocomm Research, Singapore
Alvin Martin NIST, USA
Douglas Reynolds MIT Lincoln Lab, USA
------------------------------------------------------------------------
SCIENTIFIC REVIEW COMMITTEE:
Eliathamby Ambikairajah Univ. New South Wales, Australia
Tim Anderson Air Force Research Lab, USA
Walt Andrews BBN, USA
Hagai Aronowitz IBM Haifa Research Lab, Israel
Roland Auckenthaler NMS Comm., USA
Claude Barras LIMSI, France
Kay Berkling Inline, Intern. Online Dienste GmbH, Germany
Jean-Francois Bonastre Univ. Avignon, France
Hynek Boril Univ. Texas at Dallas, USA
Niko Brummer AGNITIO, South Africa
Lukas Burget Brno Univ. Tech, Czech Republic
Joseph Campbell MITLL, USA
Bill Campbell MITLL, USA
Jan 'Honza' Cernocky Brno Univ. Tech, Czech Republic
Nancy Chen I2R, Singapore
Sandro Cumani Brno Univ. Tech, Czech Republic
Najim Dehak MIT, USA
George Doddington US. Gov. Consultant, USA
Nicholas Evans EURECOM, France
Mauro Falcone Fondazione Ugo Bordoni, Italy
Kevin Farrell Nuance, USA
Benoit Fauve Validsoft, UK
Daniel Garcia-Romero Johns Hopkins Univ, USA
Ondrej Glembek Brno Univ. Tech, Czech Republic
Joaquin Gonzalez-Rodriguez Univ. Autónoma de Madrid, Spain
Craig Greenberg NIST, USA
Cemal Hanilci Uludag Univ., Turkey
John H.L. Hansen Univ. Texas at Dallas, USA
Taufiq Hasan Univ. Texas at Dallas, USA
Ville Hautamaki Univ. Eastern Finland, Finland
Hynek Hermansky Johns Hopkins Univ, USA
Chien-Lin Huang National Inst. Inf. and Comm. Tech., Japan
Michael Jessen Bundeskriminalamt, Germany
Patrick Kenny CRIM, Canada
Tomi Kinnunen Univ. Eastern Finland, Finland
Tina Kohler DoD, USA
Pietro Laface Politecnico di Torino, Italy
Anthony Larcher I2R, Singapore
Kong Aik Lee I2R, Singapore
Yun Lei SRI International, USA
Cheung-Chi Leung I2R, Singapore
Haizhou Li I2R, Singapore
Ming Li Sun Yat-sen Univ, China
Bin Ma I2R, Singapore
Dave Marks Sandia, DoE National Labs, USA
Alvin Martin NIST, USA
David Martinez Univ. Zaragoza, Spain
John Mason Swansea Univ, UK
Pavel Matejka Brno Univ. Tech, Czech Republic
Driss Matrouf Univ. Avignon, France
Tomoko Matsui Inst. Stat. Math, Japan
Yuri Matveev ITMO University, Russia
Alan McCree Johns Hopkins Univ, USA
Pejman Mowlaee Graz Univ. Tech., Austria
Jiri Navratil IBM Research, USA
Raymond W.M. Ng Univ. Sheffield, UK
Javier Ortega-Garcia Univ. Autónoma de Madrid, Spain
Jason Pelecanos IBM Research, USA
Oldrich Plchot Brno Univ. Tech, Czech Republic
Padmanabhan Rajan Univ. Eastern Finland, Finland
Daniel Ramos Univ. Autónoma de Madrid, Spain
Douglas Reynolds MITLL, USA
Fred Richardson MITLL, USA
Rahim Saeidi Univ. Eastern Finland, Finland
Nicolas Scheffer SRI International, USA
Jan Silovsky TU Liberec, Czech Republic
Themos Stafylakis CRIM, Canada
Doug Sturim MITLL, USA
Rong Tong I2R, Singapore
Pedro Torres-Carrasquillo MITLL, USA
Michael Wagner Univ. Canberra, Australia
David van Leeuwen Radboud Univ. Nijmegen, The Netherlands
Jesus Villalba Univ. Zaragoza, Spain
Changhuai You I2R, Singapore
------------------------------------------------------------------------
VENUE AND TRAVEL:
Odyssey 2014 will be hosted by School of Computing of the University of
Eastern Finland (UEF). Joensuu is a small town of 75,000 inhabitants
in the lakeside Finland -- the capital of green. It is famous for its
peaceful nature, excellent outdoor opportunities as well as many saunas.
Joensuu can be easily reached from Helsinki (50 min flight), which can
be reached via direct flights from several European, North American
and Asian cities.
For more details:
http://cs.uef.fi/odyssey2014/
Email: odyssey@cs.uef.fi
|
