Awesome Self-Supervised Learning / 自动语音识别

vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations

作者：Alexei Baevski △ · 单位：△Facebook AI Research, Menlo Park, CA, USA, ▽University of T¨ubingen, Germany · 来源：arXiv preprint · 类别：自动语音识别 · 发布日期：2019-10-12

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
vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations figure
AlphaXiv 中文概览（可滚动查看）