arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.11269cs.CL
收藏

CSS10:10种语言的单说话人语音数据集

CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages

Kakao Brain;Expedia Group(亿客行集团)

Kyubyong Park, Thomas Mulc

摘要:

我们描述了我们的开发CSS10,一个集合的10种语言的单扬声器语音数据集。它由来自LibriVox有声读物的短音频片段及其对齐文本组成。为了验证其质量,我们在每个数据集上训练两个神经文本到语音模型。随后,我们对合成的语音样本进行平均意见得分测试。我们将我们的数据集、预训练模型和测试资源公开提供。我们希望他们将用于未来的演讲任务。

英文摘要:

We describe our development of CSS10, a collection of single speaker speech datasets for ten languages. It is composed of short audio clips from LibriVox audiobooks and their aligned texts. To validate its quality we train two neural text-to-speech models on each dataset. Subsequently, we conduct Mean Opinion Score tests on the synthesized speech samples. We make our datasets, pre-trained models, and test resources publicly available. We hope they will be used for future speech tasks.

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。

↑