Awesome Self-Supervised Learning / 自动语音识别

Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders

作者：BIDIRECTIONAL TRANSFORMER ENCODERS, Andy T. Liu, Shu-wen Yang · 来源：arXiv preprint · 类别：自动语音识别 · 发布日期：2019-10-25

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
Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders figure
AlphaXiv 中文概览（可滚动查看）