英国 Rose 言语发音训练软件 Pronunciation Coach

摘要 · 中文整理：本研究的目的是开发一种模拟英语发音动作的软体机器人舌，以支持英语发音学习。该结构由三个主要的软体执行器构成。舌系统与执行器所用材料为 Ecoflex 00-30 弹性体。研究开展了有限元方法（FEM）仿真以确认变形模式，并将结果与三维动画软件 Pronunciation Coach 3D 进行对比。结果表明，在 120 kPa 气压下，弯曲、隆起与拍动变形与该三维动画软件的演示接近。但气压参数仍需调整，以使舌模型的运动速度能够跟随人体舌的运动。

原文摘要：The purpose of this research is to develop the soft robotic tongue to mimic the movements of English pronunciation aiming at the learning support for English pronunciation. The structure consists of three primary soft actuators. The material applied to the tongue system and the actuator is an Ecoflex 00-30 elastomer. Finite Element Methods (FEM) simulations were conducted to confirm the deformation patterns and compare the results from the 3D animated software Pronunciation Coach 3D. The results show that the bend, bulge, and flap deformation are close to the 3D animated software demonstration with a pressure of 120 kPa. However, the pressure parameter needs an adjustment so the velocity of the tongue model can follow human tongue movements.

关键词：软体机器人舌、英语发音、软体执行器、Ecoflex 00-30 硅橡胶、有限元方法仿真、学习支援

研究目标：解决日语母语者学习英语发音时看不到、也学不会舌部运动方式的问题：此前用人形机器人做发音与韵律教学时，学习者反映不知道发 /r/、/l/、θ 与 ð、/f/、/v/ 等音时舌头该怎么动，而所用人形机器人没有可动的口与舌，因此需要一种能把发音时舌运动实体可视化的机器人舌。

主要结论：以发音训练软件三维动画归纳出的弯曲、隆起、卷曲三类基本运动为设计依据，采用 Ecoflex 00-30 与三组气动网络执行器构成的软体机器人舌，在 120 kPa 气压下的有限元仿真变形与软件三维发音动画演示接近，验证了系统设计与执行器布置的可行性；但运动速度尚未达到人舌水平，气压加载参数需要进一步调整。

创新点：把面向言语康复与英语发音训练的三维发音可视化软件用作机器人设计的运动学数据源，从其三维发音动画中提取并归一化舌运动参数，进而设计出可同时实现弯曲、隆起、卷曲三类英语发音舌运动的多执行器软体机器人舌，并用有限元仿真与软件动画互为校验。

后续建议：引入电磁发音仪、超声舌成像等真人发音生理测量数据，与软件三维动画参数互相校正，提高运动模板的真实性；对气压加载曲线做动态控制设计，缩短卷曲变形达到稳态所需时间，使运动速度贴近真人发音；增加软腭、下颌、唇部等联动部件，使机器人可呈现完整的音段发音姿态而非仅舌运动；在实际英语学习者群体中开展对照实验，验证观察机器人舌运动对发音习得的实际增益；为执行器嵌入柔性弯曲传感器，实现闭环反馈控制与变形参数在线测量

APA 引文：Krisdityawan, E., Yokota, S., Matsumoto, A., Chugo, D., Muramatsu, S., & Hashimoto, H. (2023). Soft robotic tongue that mimicking English pronunciation movements. In 2023 IEEE International Conference on Mechatronics (ICM) (pp. 1-5). IEEE. https://doi.org/10.1109/ICM54990.2023.10102027

仪器引用：Finite Element Methods (FEM) simulations were conducted to confirm the deformation patterns and compare the results from the 3D animated software Pronunciation Coach 3D.

摘要 · 中文整理：本文提出了一种模拟英语发音动作的新型软体机器人舌，旨在为英语发音学习提供支援。此前已提出软体机器人舌的系统设计与执行器布置，并针对各类变形开展了有限元方法（FEM）仿真。本文讨论两个阶段性成果：制作与实验评估。样机采用模具成型与浇注方法制作，尺寸放大为人体舌原始尺寸的五倍；使用硅橡胶 Ecoflex 00-30 浇注到预先用 3D 打印机打印的模具中。此外还开展实验以确认并评估英语发音动作的变形模式，使用直尺测量各类变形的参数，如弯曲角、拍动角与隆起高度。结果表明，所制作的软体机器人舌与 FEM 仿真结果在弯曲与隆起变形上基本一致；但在实验评估中拍动变形存在小幅差异。

原文摘要：A novel soft robotic tongue mimicking the movements of English pronunciation was proposed, aiming at the learning support for English pronunciation. A soft robotic tongue's system design and actuator arrangements have been proposed, and the Finite Element Methods (FEM) simulation for each deformation has been conducted. In this paper, we discussed two milestones: fabrication and experimental evaluation. The fabrication, molding, and casting method was applied to the model, and it was manufactured five times bigger than the original size of a human tongue. A silicone rubber Ecoflex 00-30 was utilized and poured into the mold that was preliminary printed with a 3D printer. Moreover, an experiment was conducted to confirm and evaluate the deformation patterns of English pronunciation movements. A ruler was used to measure the parameters in each deformation, such as bend and flap angle, and bulge height. It presented that bend and bulge deformations between the fabricated soft robotic tongue and simulated FEM results were likely the same; however, the flap deformation slightly differed in the experimental evaluation.

关键词：软体机器人舌、气动网络、制作工艺、英语发音

研究目标：解决仿真设计如何落地为实体的问题：需要确认按发音软件动画参数设计、并经有限元仿真验证的软体机器人舌，在实际制作后能否在气压驱动下真实复现英语发音时的弯曲、隆起与卷曲三类舌运动，以及实测变形与仿真之间存在多大偏差。

主要结论：采用 Ecoflex 00-30 弹性体与 3D 打印模具的浇注工艺，成功制作出 5 倍放大的软体机器人舌；气压实验表明弯曲与隆起变形与有限元仿真结果基本一致，卷曲变形存在约 4 度偏差且左右不对称，推测由卷曲执行器内腔壁厚的制作误差引起；尽管数值存在差异，只要机器人能在视觉上再现发音软件所示的舌运动，其作为发音学习支持工具的实用价值依然成立。

创新点：给出了从发音可视化软件动画到实体软体机器人的完整实现链条：以 Pronunciation Coach 3D 动画为运动基准提取参数，经有限元仿真、5 倍放大模具浇注制作，再用直尺测量与三角几何换算完成仿真—实验双向校验，并搭建了 Arduino 加三路电气比例调压阀的独立多执行器气压驱动系统。

后续建议：改用柔性弯曲传感器或视觉动作捕捉替代直尺人工测量，提高变形参数的测量精度与可重复性；重新设计卷曲执行器的内腔壁厚并严格控制制作公差，消除左右变形不对称；开展动力学状态分析，实现各执行器变形的参数化闭环控制；增加仿真舌套等外观覆盖件，提升实际教学场景中的可接受度；与真人发音的舌运动测量数据做量化对照，而不仅与软件动画做视觉比对

APA 引文：Krisdityawan, E., Yokota, S., Matsumoto, A., Chugo, D., Muramatsu, S., & Hashimoto, H. (2023). Soft robotic tongue mimicking English pronunciation movements 2nd report: Fabrication and experimental evaluation. In Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics (ICINCO 2023) - Volume 1 (pp. 704-710). SCITEPRESS. https://doi.org/10.5220/0012207800003543

仪器引用：We analyzed the basic movements using software called "Pronunciation Coach 3D" (icSpeech, n.d.). Basic tongue movements during pronouncing English sounds are distinguished into three movements: bend, bulge, and flap shown in Figure 1.