Blizzard Challenge 2013 Workshop

The Blizzard Challenge 2013 Workshop evening reception is generously sponsored by IVONA http://www.ivona.com/

Tuesday 3rd September 2013

The workshop will be at UPC in Barcelona.

Call for participation

The Blizzard Challenge 2013 Workshop is the culmination of the Blizzard Challenge 2013 which is an open speech synthesis evaluation campaign using common data sets and a large listening test. The aims of the workshop are to present the results from the listening tests and for participants in the Challenge to describe their systems.

The workshop is a satellite of Interspeech 2013

Who can attend the workshop ?

The workshop is open to all and we encourage participation from anyone interested in speech synthesis.

Who can submit a paper to the workshop ?

All participants in the Challenge are expected to submit a paper describing their entry (even if they cannot attend the workshop in person). Papers will be refereed by the Programme Committee.

Programme Committee

• Simon King, University of Edinburgh, UK
• Alan Black, Carnegie Mellon Univerisity, USA
• Keiichi Tokuda, Nagoya Institute of Technology, Japan
• Kishore Prahallad, IIITH, India

Paper submission instructions

• Use the Interspeech 2013 authors' kit, but your paper should be up to SIX pages in length
• Remember that Blizzard is a scientific investigation - we are all trying to understand why some techniques work better than others.
• With this in mind, please write a detailed, technical paper aimed at a specialist audience. Focus on analysis and evaluation. Try to explain WHY your system performed the way it did, and what makes it different from other systems. Explain why your system is designed in a particular way. For example, report internal evaluations you have done to select certain methods.
• Submit your paper by email to blizzard@festvox.org by the 26th July 2013 and we will notify you of acceptance within a week. If you need an earlier notification (e.g., in order to obtain travel permission from your employer), then please contact us.

Location and date

Date: Tuesday 3rd September 2013 (all day)

Venue:

Universitat Politècnica de Catalunya

Campus Diagonal Nord

C. Jordi Girona, 1-3

08034 Barcelona

Spain

UPC campus maps

Room: Aula Master in Building A3

Metro: Line L3 to Zona Universitària

Programme

The workshop format is single-track with oral presentations from the participants in the Challenge, the organisers and invited speakers.

Each system presentation should last for a maximum of 15 minutes, plus a few minutes for questions. Presenters should bear in mind that the audience will mainly comprise speech synthesis experts; therefore presentations do not need to include extensive background material.

We will start at 11am and run until around 8pm. The provisional programme is as follows:

• 11.00 - 12.00 Welcome, introduction, summary of results
  • Welcome from Simon King, on behalf of the organisers
  • Message from data providers (TBC)
  • Message from evening reception sponsor
  • Summary of English results from Simon King
  • Summary of Indian languages results from Kishore Prahallad

• 12.00 - 13.00 System presentations (15 minutes each + questions)
  • DFKI Deutsche Forschungszentrum für Künstliche Intelligenz, Germany
  • CMU Carnegie Mellon University, USA
  • MERAKA Meraka Institute, South Africa

• 13.00 - 15.00 Lunch

• 15.00 - 16.20 System presentations (15 minutes each + questions)
  • I2R Institute for Infocomm Research, Singapore
  • S4A Simple4All project consortium, various countries
  • ISOLAR Institute of Information Technology - Vietnam Academy of Technology / iSolar Company, Vietnam
  • RACAI Research Institute for Artificial Intelligence, Romanian Academy, Romania

• 16.20 Coffee break

• 17.00 - 18.00 System presentations (20 minutes each)
  • MILE-TTS Dept. of Electrical Engg, Indian Institute of Science, India
  • LESSAC Lessac Technologies Inc, USA
  • ILSP Institute for Language & Speech Processing / Innoetics, Greece

• 18.00 Coffee break

• 18.30 - 19.30 System presentations (15 minutes each + questions)
  • NITECH Nagoya Institute of Technology, Japan
  • USTC National Engineering Laboratory of Speech and Language Information Processing, China
  • SHRC Speech and Hearing Research Center, Peking University, China

• 19.30 Wrap-up and discussion

• ~20.30 Evening reception, sponsored by IVONA

Not able to attend the workshop: NTUT National Taipei University of Technology, Taiwan

Practical information

Registration

Registration procedure

Registration is now closed. If you wish to attend, please contact blizzard@festvox.org to find out if there are any spare places.

Cost

There is no charge to attend the Blizzard Workshop, thanks to the generosity of UPC and the kind assistance of Antonio Bonafonte. There will be a modest charge for catering, payable on-site in cash (estimate: 30 euros per delegate).

Accommodation and travel

Same as SSW8

Published proceedings

The papers will be published on festvox.org