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

Interspeech (2019)

초록

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.

저자

박규병 (카카오브레인), Thomas Mulc (익스피디아)

키워드

speech TTS(text-to-speech)

발행 날짜

2019.05.27