[hts-users:04669] JVS-MuSiC: free Japanese multispeaker singing-voice corpus
Dear speech researchers,
We are pleased to inform you that a new Japanese multi-speaker singing-voice corpus is freely available at:
https://sites.google.com/site/shinnosuketakamichi/research-topics/jvs_music
This corpus consists of multi-speaker singing-voice data. The specification is as follows.
- 100 singers (their reading voices are stored in the JVS corpus.)
- Each singer sung 2 songs;
* A Japanese child-song "katatsumuri" as a common song (raw.wav). Also included:
* The edited version whose pitch and tempo are modified for each singer.
* The edited version whose pitch and tempo are unified among singers.
* Melodyne project files that are used for modifying and unifying.
* Other child-songs that are different among singers
- High-quality (studio recording), high-sampling-rate (24 kHz)
- Useful tags included (e.g., singer similarity, key, tempo)
The tags are licensed with CC BY-SA 4.0. The audio data and Melodyne project files may be used for
- Research by academic institutions
- Non-commercial research, including research conducted within commercial organizations
- Personal use, including blog posts.
If you want to use for commercial purposes, please see our project page. Re-distribution is not permitted, but you can upload a part of this corpus (e.g., ~3 audio files) in your webpage or blog. If possible, please let me know when you revealed papers, blog posts, and others. It will be very helpful to investigate the contributions of this corpus.
Best,
--
Shinnosuke TAKAMICHI, Ph.D.
Assistant Professor of The University of Tokyo
shinnosuke_takamichi@xxxxxxxxxxxxxxxxxxx