基于统计形状模型的发音数据实时视觉反馈框架
人机交互
2016-12-20 v1
摘要
我们提出一个新颖的开源框架，用于实时可视化电磁发音描记术 (EMA) 数据，该框架采用模块化架构，并利用多线性子空间学习导出的解剖学精确的舌头与上颚模型。
引用
@article{arxiv.1612.06114,
title = {A real-time framework for visual feedback of articulatory data using statistical shape models},
author = {Kristy James and Alexander Hewer and Ingmar Steiner and Stefanie Wuhrer},
journal= {arXiv preprint arXiv:1612.06114},
year = {2016}
}
备注
17th Annual Conference of the International Speech Communication Association (Interspeech), Oct 2016, San Francisco, United States