Awesome Self-Supervised Learning / 自动语音识别

TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech

作者：作者信息待提取 · 单位：ip of National Taiwan University and in part by ASUS, ering, College of Electrical Engineering and Com · 来源：arXiv preprint · 类别：自动语音识别 · 发布日期：2020-07-12

自监督学习表征学习音频自动语音识别
新标签打开 AlphaXiv新标签打开 Code
TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech figure
AlphaXiv 中文概览（可滚动查看）