[hts-users:04671] Voice Conversion Challenge 2020
Dear all,
We warmly invite you to participate in the third Voice Conversion
Challenge, "Voice Conversion Challenge 2020."
The purpose of this challenge is to compare different approaches for
converting source speakers' voices into different target speakers'
voices included in the common corpus provided by organizers and to
deeply understand the current performance and remaining issues of the
voice conversion technology. Naturalness and similarity scores of the
converted speech will be evaluated via listening tests.
In the previous challenges held in 2016 and 2018, we focused on voice
conversion strategies using a parallel corpus and/or a nonparallel
corpus within the same language. In the third challenge, we will release
a new database and protocols that allow participants to build their
voice conversion systems based on non-parallel data within the same
language and/or over different languages. We will provide one or a few
baseline scripts for training voice conversion systems. For more
details, please see http://vc-challenge.org/
The current schedule is as follows:
- Mar. 9th, 2020: release of training data (and registration deadline)
- May 11th, 2020: release of evaluation data
- May 18th, 2020: deadline to submit the converted audio
- July 20th, 2020: notification of results
Likewise the previous challenges, there is no participation fee.
Interested participants should do online registration of the information
of your team at http://bit.ly/39LrAcB by Mar. 9th, 2020.
Please freely contact us if you have questions.
Looking forward to hear from you.
Regards,
--
The Voice Conversion Challenge 2020 Organizers
Tomoki Toda & Wen-Chin Huang (Nagoya University)
Junichi Yamagishi (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)