papers AI Learner
The Github is limit! Click to go to the new site.

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

2019-03-27
Kyubyong Park, Thomas Mulc

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.11269

PDF

http://arxiv.org/pdf/1903.11269


Comments

Content