Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020

From SynSIG
<div class="mw-revision"><div id="mw-revision-info">Revision as of 11:45, 23 October 2021 by <a href="/index.php?title=User:Simon.King&amp;action=edit&amp;redlink=1" class="new mw-userlink" title="User:Simon.King (page does not exist)"><bdi>Simon.King</bdi></a> <span class="mw-usertoollinks">(<a href="/index.php?title=User_talk:Simon.King&amp;action=edit&amp;redlink=1" class="new mw-usertoollinks-talk" title="User talk:Simon.King (page does not exist)">talk</a> | <a href="/index.php/Special:Contributions/Simon.King" class="mw-usertoollinks-contribs" title="Special:Contributions/Simon.King">contribs</a>)</span></div><div id="mw-revision-nav">(<a href="/index.php?title=Joint_Workshop_for_the_Blizzard_Challenge_and_Voice_Conversion_Challenge_2020&amp;diff=prev&amp;oldid=2983" title="Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020">diff</a>) <a href="/index.php?title=Joint_Workshop_for_the_Blizzard_Challenge_and_Voice_Conversion_Challenge_2020&amp;direction=prev&amp;oldid=2983" title="Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020">← Older revision</a> | Latest revision (diff) | Newer revision → (diff)</div></div>

The Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020 is a satellite workshop of Interspeech2020.

Call for participation

The Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020 is the culmination of the Blizzard Challenge 2020 and the Voice Conversion Challenge 2020. Blizzard Challenge is an annual challenge to compare corpus-based speech synthesis on common databases and has history of 15 years. Voice Conversion Challenge is a biannual challenge to compare different voice conversion systems and approaches using the same voice data. This is a joint workshop of the sixteenth edition of the Blizzard challenge and third edition of the Voice Conversion Challenge. The aims of the workshop are to present the results from the listening tests and for participants in both challenges 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 and voice conversion. However, please follow the registration procedure below.

Who can submit a paper to the workshop ?

All participants in the Blizzard Challenge 2020 are required to submit a paper describing their entry. All participants in the Voice Conversion Challenge 2020 are invited to submit one paper that summarizes their system and shows some results. The paper submission instructions can be found at Blizzard Challenge 2020 Rules #PAPER and VCC2020 website.

Organizers of the Blizzard Challenge 2020

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

Organizers of the Voice Conversion Challenge 2020

  • Tomoki Toda & Wen-Chin Huang (Nagoya University)
  • Junichi Yamagishi & Yi Zhao (National Institute of Informatics)
  • Tomi Kinnunen (University of Eastern Finland)
  • Zhenhua Ling (University of Science and Technology of China)
  • Rohan Kumar Das & Xiaohai Tian (National University of Singapore)

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: Friday 30th October 2020

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

There will be two formats of presentation, Live Oral Presentation and Pre-Recorded Video Presentation. The duration of each presentation is listed in the tentative program below. The instruction of uploading video recordings will be announced soon. 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).

  • 18:00 - 18:10 Welcome message

Blizzard Challenge 2020 Session (Chair: Zhenhua Ling)

  • 18:10 - 18:25 Live Oral Presentation
    • The Blizzard Challenge 2020 (Presenter: Zhenhua Ling)
  • 18:25 - 19:10 Live Oral Presentations (15 mins each including 5 mins Q&A)
    • The SHNU System for Blizzard Challenge 2020 (Presenter: Laipeng He)
    • The OPPO System for the Blizzard Challenge 2020 (presenter: Kun Xie)
    • The Tencent speech synthesis system for Blizzard Challenge 2020 (Presenter: Zewang Zhang)
  • 19:10 - 19:40 Pre-Recorded Video Presentations (2.5 mins each, plus 7.5 mins Q&A after all 9 presentations)
    • The Duke Entry for 2020 Blizzard Challenge
    • Submission from SCUT for Blizzard Challenge 2020
    • NUS-HLT System for Blizzard Challenge 2020
    • The Sogou System for Blizzard Challenge 2020
    • The RoyalFlush Synthesis System for Blizzard Challenge 2020
    • The Ximalaya TTS System for Blizzard Challenge 2020
    • The HITSZ TTS system for Blizzard challenge 2020
    • The NLPR Speech Synthesis entry for Blizzard Challenge 2020
    • The Ajmide Text-To-Speech System for Blizzard Challenge 2020
  • 19:40 - 19:55 Open discussion for Blizzard Challenge
  • 19:55 - 20:10 Break
  • 20:10 - 20:15 Announcement on Speech Synthesis Workshop (SSW) 11(Presenter: Géza Németh)

Voice Conversion Challenge 2020 Session (Chair: Tomoki Toda)

  • 20:15 - 20:55 Live Oral Presentations
    • Voice Conversion Challenge 2020 –- Intra-lingual semi-parallel and cross-lingual voice conversion (Presenter: VCC 2020 team)
    • Predictions of Subjective Ratings and Spoofing Assessments of Voice Conversion Challenge 2020 Submissions (Presenter: VCC 2020 team)
  • 20:55 - 21:40 Live Oral Presentations (15 mins each including 5 mins Q&A)
    • Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody Transfer & Non-Parallel Voice Conversion with Autoregressive Conversion Model and Duration Adjustment (Presenter: Jing-Xuan Zhang & Li-Juan Liu)
    • Submission from SRCB for Voice Conversion Challenge 2020 (Presenter: Qiuyue Ma)
    • CASIA Voice Conversion System for the Voice Conversion Challenge (Presenter: Zheng Lian)
  • 21:40 - 22:25 Pre-Recorded Video Presentations (5 mins for each technical paper and 2.5 mins each for each system description paper, plus 15 mins Q&A after all 10 presentations)
    • Technical Papers
      • Non-parallel Voice Conversion based on Hierarchical Latent Embedding Vector Quantized Variational Autoencoder
      • FastVC: Fast Voice Conversion with non-parallel data
      • Latent linguistic embedding for cross-lingual text-to-speech and voice conversion
    • System Description Papers
      • Baseline System of Voice Conversion Challenge 2020 with Cyclic Variational Autoencoder and Parallel WaveGAN
      • The Sequence-to-Sequence Baseline for the Voice Conversion Challenge 2020: Cascading ASR and TTS
      • The NU Voice Conversion System for the Voice Conversion Challenge 2020: On the Effectiveness of Sequence-to-sequence Models and Autoregressive Neural Vocoders
      • The NUS & NWPU system for Voice Conversion Challenge 2020
      • The NeteaseGames System for Voice Conversion Challenge 2020 with Vector-quantization Variational Autoencoder and WaveNet
      • The Academia Sinica Systems of Voice Conversion for VCC2020
      • The UFRJ Entry for the Voice Conversion Challenge 2020
  • 22:25 - 22:40 Open discussion for Voice Conversion Challenge


Published proceedings

The papers are published on festvox.org


SynSIG is a Special Interest Group of ISCA, the International Speech Communication Association.

SynSIG 1998-2022