KiSing: the First Open-source Mandarin Singing Voice Synthesis Corpus

We are pleased to publish KiSing, the first open-source Mandarin singing corpus built specifically for singing voice synthesis (SVS).

Corpus Specifics

This corpus consists of singing voices and their corresponding musical and phonetic annotation. The specification is as follows.

• 14 songs from Keyi (Kiki) Zhang (composer, lyricist, singer)
• High quality (recorded in a professional recording studio) and high sampling rate (48 kHz)
• Free for non-commercial use (See “terms of use”)
• Other useful data (MIDI, phoneme labels with specific duration information)

Download

Segmented singing, midi, and phonetic label

The Singer

Keyi (Kiki) Zhang, 张钶浥, is a talented Chinese female singer, composer, and lyricist. She has published around 30 songs with a variety of styles. The KiSing corpus, named after her name Kiki, mainly consists of some of his published songs. Those songs with accompaniments can be found in both QQ music and Netease Cloud Music. Feel free to check them out!

Term of Use

All the data in the corpus is licensed with Creative Commons Attribution-NonCommercial-NoDerivs 4.0 (CC BY-NC-ND 4.0).

Main Contributors

Jiatong Shi, The Johns Hopkins University, jiatong_shi@jhu.edu

Keyi (Kiki) Zhang, the singer, composer, and lyricist

Zhaodong Yao, the writer for the music score (i.e., MIDI) annotation

Other Resources

The corresponding recipe to train a singing voice synthesis system will be released soon in Muskits

Citation

Shi, J., Guo, S., Qian, T., Hayashi, T., Wu, Y., Xu, F., Chang, X., Li, H., Wu, P., Watanabe, S., Jin, Q. (2022) Muskits: an End-to-end Music Processing Toolkit for Singing Voice Synthesis. Proc. Interspeech 2022, 4277-4281, doi: 10.21437/Interspeech.2022-10039

@inproceedings{shi22d_interspeech,
  author={Jiatong Shi and Shuai Guo and Tao Qian and Tomoki Hayashi and Yuning Wu and Fangzheng Xu and Xuankai Chang and Huazhe Li and Peter Wu and Shinji Watanabe and Qin Jin},
  title={{Muskits: an End-to-end Music Processing Toolkit for Singing Voice Synthesis}},
  year=2022,
  booktitle={Proc. Interspeech 2022},
  pages={4277--4281},
  doi={10.21437/Interspeech.2022-10039},
  issn={2958-1796}
}

Acknowledgment

The project is under the support of the AIM3 lab from Renmin University of China. We would also like to thank Bingrong Shi and Yunhong Wei for correcting the phonetic alignment.