J-MAC：用于语音合成的日语多说话人有声读物语料库
J-MAC: Japanese multi-speaker audiobook corpus for speech synthesis
摘要：
在本文中，我们构建了一个日语有声读物语音语料库称为“J-MAC”的语音合成研究。随着阅读式语音合成的成功，其研究对象逐渐转向使用复杂语境的任务。有声读物语音合成就是一个很好的例子，它需要跨句子、表达力等。与阅读式语音不同，有声读物语音中特定于说话人的表达力也成为上下文。为了加强这一研究，我们提出了一种方法来构建一个语料库从有声读物阅读的专业人士。从许多有声读物及其文本中，我们的方法可以自动提取和提炼数据，而不依赖于任何语言。具体来说，我们使用声乐乐器分离来提取干净的数据，连接主义的时间分类来粗略对齐文本和音频，语音活动检测来细化对齐。J-MAC在我们的项目页面中是开源的。我们还进行有声读物语音合成的评估，结果给有声读物语音合成的见解。
英文摘要：
In this paper, we construct a Japanese audiobook speech corpus called "J-MAC" for speech synthesis research. With the success of reading-style speech synthesis, the research target is shifting to tasks that use complicated contexts. Audiobook speech synthesis is a good example that requires cross-sentence, expressiveness, etc. Unlike reading-style speech, speaker-specific expressiveness in audiobook speech also becomes the context. To enhance this research, we propose a method of constructing a corpus from audiobooks read by professional speakers. From many audiobooks and their texts, our method can automatically extract and refine the data without any language dependency. Specifically, we use vocal-instrumental separation to extract clean data, connectionist temporal classification to roughly align text and audio, and voice activity detection to refine the alignment. J-MAC is open-sourced in our project page. We also conduct audiobook speech synthesis evaluations, and the results give insights into audiobook speech synthesis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
