Blizzard Challenge 2021 Workshop

Call for participation

The Blizzard Challenge 2021 Workshop is the culmination of the Blizzard Challenge 2021. Blizzard Challenge is an annual challenge to compare corpus-based speech synthesis on common databases 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.

Who can attend the workshop ?

The workshop is open to all and we encourage participation from anyone interested in speech synthesis. However, please follow the registration procedure below.

Who can submit a paper to the workshop ?

All participants in the Blizzard Challenge 2021 are required to submit a paper describing their entry. The paper submission instructions can be found at Blizzard Challenge 2021 Rules #PAPER.

Organizers of the Blizzard Challenge 2021

• Zhenhua Ling & Xiao Zhou (University of Science and Technology of China)
• Simon King (University of Edinburgh)

Location and date

Online event

The workshop will be held online using Zoom. The meeting ID and password will be sent to registered participants by email later.

Date: Saturday 23rd October 2021

Registration

Please click here to make the workshop registration. At least one author of each accepted paper should register to present the paper and answer questions.

Programme

We will have Live Oral Presentation for all accepted papers. The duration of each presentation is 12 mins (including 2 mins Q&A). All presentations will be recorded and videos will be uploaded to SynSIG youtube account if permissions are given.

All times here are in Beijing time (GMT+8).

• 19:00 - 19:20 Welcome message and Summary of Blizzard Challenge 2021 (Presenter: Zhenhua Ling)

• 19:20 - 20:08 System presentations, 4 * 12 mins (Chair: Simon King)
  • University of Stuttgart, Germany, Institute for Natural Language Processing, Digital Phonetics Research Group
  • Institute of Acoustics, Chinese Academy of Sciences
  • Tencent
  • Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València (UPV)

• 20:08 - 20:20 Additional Q&A and break

• 20:20 - 21:20 System presentations, 5 * 12 mins (Chair: Zhenhua Ling)
  • CPQD Foundation and University of Campinas (Unicamp)
  • Trinity College Dublin
  • South China University of Technology
  • CSTR, University of Edinburgh
  • Samsung Research China - Beijing (SRCB)

• 21:20 - 21:30 Additional Q&A and break

• 21:30 - 22:18 System presentations, 4 * 12 mins (Chair: Simon King)
  • University of the Basque Country (UPV/EHU) - Aholab Signal Processing Laboratory
  • Singapore University of Technology and Design, Singapore National University of Singapore
  • TAL
  • Microsoft

• 22:18 - 22:30 Additional Q&A and closing remarks

Published proceedings

The papers are published on festvox.org