Voice Conversion Challenge
We are glad to invite you to participate in the 1st Voice Conversion Challenge to compare different voice conversion systems and approaches using the same voice data.
Task of the 1st Challenge
The task is speaker conversion, which is a well-known basic task in voice conversion.
- We will provide voices of 5 source and 5 target speakers (consisting of both female and male speakers) from fixed corpora as training data. Each speaker utters the same sentence set consisting of around 150 sentences.
- Using these parallel data sets, voice conversion systems for all speaker-pair combinations (25 speaker-pairs in total) will be developed by each participant.
- Other voices of the same source speakers will be provided later as test data that consists of around 50 sentences for each speaker. Each participant will generate converted voices from them using the developed 25 conversion systems.
- The resulting 25 converted voice sets will be evaluated in terms of perceived naturalness and similarity with listening tests.
We focus on 16 kHz speech and signal-to-signal conversion strategies. No transcription will be provided and the use of phonetic information given manually is NOT allowed. Participants are free of using additional data (for training purposes) different from the database from which the speakers corpora will be provided.
The tentative schedule is as follows:
- November 25th: release of training data
- January 8th: release of evaluation data
- January 15th: deadline to submit the converted audio.
- February 29th: notification of results
How to Participate?
There is no fee for registration.
We invite however participants to notify your intention to participate by November 23rd.
Please email to email@example.com if you want to participate in the challenge. Although we will start to realease the training data on November 25th, we will also accept the entry for a while after that.
⇒ The registration is now closed.
Participants need to strictly follow the Challenge rules. Please carefully read the following page:
Summary of the Challenge is shown in the following page:
This work was supported in part by
- Linghui Chen (University of Science and Technology of China)
- Daisuke Saito (Tokyo University)
- Tomoki Toda (Nagoya University)
- Fernando Villavicencio (National Institute of Informatics)
- Mirjam Wester (University of Edinburgh)
- Zhizheng Wu (University of Edinburgh)
- Junichi Yamagishi (National Institute of Informatics)
Contact information: firstname.lastname@example.org