Model-based inverse estimation for active contraction stresses of tongue muscles using 3D surface shape in speech production
Model-based inverse estimation for active contraction stresses of tongue muscles using 3D surface shape in speech production
复制标题
基于模型的言语产生中使用 3D 表面形状的舌肌主动收缩应力的逆估计
DOI：
10.1016/j.jbiomech.2017.09.008
复制
发表时间：
2017
影响因子：
2.4
通讯作者：
Wada Shigeo
中科院分区：
文献类型：
--
作者：
Koike Narihiko;Ii Satoshi;Yoshinaga Tsukasa;Nozaki Kazunori;Wada Shigeo
本文提出了一种新的舌肌主动收缩应力逆估计方法。该方法基于变分数据同化，利用机械舌模型和三维舌面形状进行语音生成。机械舌模型考虑了非线性超弹性、有限变形、计算机断层扫描（CT）图像的实际几何形状和肌肉纤维的各向异性主动收缩，其方向理想地通过解剖图确定。采用有限元法求解静力平衡方程，得到舌形变形。建立了一个反问题，以找到肌肉收缩应力的组合，使舌面在力学分析和语音产生的CT结果之间的欧几里得距离最小，其中带符号距离函数表示舌面。我们的方法通过一个理想的数值例子得到了验证，并扩展到两个日语元音/音/音和/音/音的现实情况。结果完全捕获了目标形状，并提供了理想情况下主动收缩应力的极好估计，并且显示出与先前对实际元音情况的观察和模拟相似的趋势。该方法可以揭示相似话语中不同舌形的肌肉收缩应力之间的相对关系，并且可以仅使用医学图像中获得的舌形变形来研究言语过程中舌肌肉的协调。这将增强我们对言语运动控制的理解。
This paper presents a novel inverse estimation approach for the active contraction stresses of tongue muscles during speech. The proposed method is based on variational data assimilation using a mechanical tongue model and 3D tongue surface shapes for speech production. The mechanical tongue model considers nonlinear hyperelasticity, finite deformation, actual geometry from computed tomography (CT) images, and anisotropic active contraction by muscle fibers, the orientations of which are ideally determined using anatomical drawings. The tongue deformation is obtained by solving a stationary force-equilibrium equation using a finite element method. An inverse problem is established to find the combination of muscle contraction stresses that minimizes the Euclidean distance of the tongue surfaces between the mechanical analysis and CT results of speech production, where a signed-distance function represents the tongue surface. Our approach is validated through an ideal numerical example and extended to the real-world case of two Japanese vowels, /ʉ/ and /ɯ/. The results capture the target shape completely and provide an excellent estimation of the active contraction stresses in the ideal case, and exhibit similar tendencies as in previous observations and simulations for the actual vowel cases. The present approach can reveal the relative relationship among the muscle contraction stresses in similar utterances with different tongue shapes, and enables the investigation of the coordination of tongue muscles during speech using only the deformed tongue shape obtained from medical images. This will enhance our understanding of speech motor control.