用于流式语音识别的轻量化端到端声学架构
, 李欣 Lightweight End-to-End Architecture for Streaming Speech Recognition
YANG Shuying1 , LI Xin1
, LI Xin 
用于流式语音识别的轻量化端到端声学架构 |
|
杨淑莹, 李欣 |
Lightweight End-to-End Architecture for Streaming Speech Recognition |
|
YANG Shuying
, LI Xin |
| 采用基于历史的自注意力交互机制的音频编码器的预测输出和注意力矩阵 |
| |