Hi-Fi Multi-Speaker English TTS Dataset 本文是NVIDIA在2021.04.03更新的文章,主要为促进tts的multi-speaker的研究,对LibriVox进行处理,获取11speakers的300小时的训练语料,具体文章链接 arxiv.org/pdf/2104.0149 (数据还没放出来,先做个笔记吧) 内容摘要: 本文提到现有的开源TTS数据中高质量的数据很少,因此本文设计...
语音合成论文优:开源数据Hi-Fi Multi-Speaker English TTS Dataset,程序员大本营,技术文章内容聚合第一站。
Hi-Fi Multi-Speaker English TTS Dataset (Hi-Fi TTS) is a multi-speaker English dataset for training text-to-speech models. The dataset is based on public audiobooks from LibriVox and texts from Project Gutenberg. The Hi-Fi TTS dataset contains about 291.6 hours of speech from 10 speakers ...