JVS-MuSiC: Japanese multispeaker singing-voice corpus
This provides a new dataset for singing-voice synthesis research, addressing a gap for researchers in this domain, though it is incremental as it builds on existing single-singer corpora.
The authors tackled the lack of a multispeaker singing-voice corpus by creating JVS-MuSiC, a Japanese dataset with 100 singers, and found a moderate correlation between singing-voice similarity and unison oneness, but a weak correlation with speech similarity.
Thanks to developments in machine learning techniques, it has become possible to synthesize high-quality singing voices of a single singer. An open multispeaker singing-voice corpus would further accelerate the research in singing-voice synthesis. However, conventional singing-voice corpora only consist of the singing voices of a single singer. We designed a Japanese multispeaker singing-voice corpus called "JVS-MuSiC" with the aim to analyze and synthesize a variety of voices. The corpus consists of 100 singers' recordings of the same song, Katatsumuri, which is a Japanese children's song. It also includes another song that is different for each singer. In this paper, we describe the design of the corpus and experimental analyses using JVS-MuSiC. We investigated the relationship between 1) the similarity of singing voices and perceptual oneness of unison singing voices and between 2) the similarity of singing voices and that of speech. The results suggest that 1) there is a positive and moderate correlation between singing-voice similarity and the oneness of unison and that 2) the correlation between singing-voice similarity and speech similarity is weak. This corpus is freely available online.