Oct, 2021
针对端到端语音识别和理解优化语音和语言潜空间的对齐
Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding
Wei Wang, Shuo Ren, Yao Qian, Shujie Liu, Yu Shi...
TL;DR本文提出引用对齐器和模态切换训练来更好地对齐语音和文本潜在空间,实验结果在 Librispeech ASR 任务和 SNIPS 槽填充任务上都表现出了显著的性能提升。