Improving ultrasound tongue image reconstruction from lip images using self-supervised learning and attention mechanism

被引：0

作者：

Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan ^{[1
]}

不详 ^{[2
]}

机构：

来源：

arXiv |

关键词：

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Attention mechanisms - Cross modality - Cross-modality mapping - Human organs - Image sequence - Images reconstruction - Speech production - Supervised learning problems - Ultrasound tongue imaging - Vocal-tracts

引用