PJS：音素平衡的日语歌唱语音语料库（CS S）---蔡秋纯

本文提出了一个免费的日语歌唱语音语料库，可用于具有高度实用性和可复制性的歌唱语音合成研究。歌唱语音语料库有助于歌唱语音合成的发展，但现有的语料库存在两个关键问题：数据不平衡（歌唱语音语料库不能保证音素平衡，不像说话语音语料库）和版权问题（不能合法共享数据）。为了避免这些问题，我们构建了一个PJS（phoneme balanced Japanese sing voice）语料库，该语料库保证了音素的平衡，并获得了CC BY-SA 4.0的许可，并且使用音素平衡的口语语料库编写了旋律。本文描述了如何构建语料库。

原文标题：PJS: phoneme-balanced Japanese singing voice corpus

原文：This paper presents a free Japanese singing voice corpus that can be used for highly applicable and reproducible singing voice synthesis research. A singing voice corpus helps develop singing voice synthesis, but existing corpora have two critical problems: data imbalance (singing voice corpora do not guarantee phoneme balance, unlike speaking-voice corpora) and copyright issues (cannot legally share data). As a way to avoid these problems, we constructed a PJS (phoneme-balanced Japanese singing voice) corpus that guarantees phoneme balance and is licensed with CC BY-SA 4.0, and we composed melodies using a phoneme-balanced speaking-voice corpus. This paper describes how we built the corpus.

原文作者：Junya Koguchi, Shinnosuke Takamichi

原文地址：https://arxiv.org/abs/2006.02959