eduzhai > Applied Sciences > Engineering >

PJS phoneme-balanced Japanese singing voice corpus

  • Save

... pages left unread,continue reading

Document pages: 3 pages

Abstract: This paper presents a free Japanese singing voice corpus that can be used forhighly applicable and reproducible singing voice synthesis research. A singingvoice corpus helps develop singing voice synthesis, but existing corpora havetwo critical problems: data imbalance (singing voice corpora do not guaranteephoneme balance, unlike speaking-voice corpora) and copyright issues (cannotlegally share data). As a way to avoid these problems, we constructed a PJS(phoneme-balanced Japanese singing voice) corpus that guarantees phonemebalance and is licensed with CC BY-SA 4.0, and we composed melodies using aphoneme-balanced speaking-voice corpus. This paper describes how we built thecorpus.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...