BACKGROUND: Tongue tracking, which helps researchers gain valuable insights into speech mechanism, has many applications in speech therapy and language learning. The wireless localization technique, which involves tracking a small magnetic tracer within the 3-D oral space, provides a low cost and convenient approach to capture tongue kinematics. In practice, this technique requires accurate calibration of three-axial magnetic sensors used in the tracking system. The data-driven calibration depends on the trajectories of magnetic tracer and the ambient noise, which may change across time and space. METHODS: In this paper, we model the kinematics of tracer movement and the noisy magnetic measurements in a Bayesian framework, then present a joint calibration and localization (JCL) algorithm based on expectation maximization (EM), where the unscented Rauch-Tung-Striebel smoother is employed for tracer localization and the curvilinear search algorithm is applied for sensor calibration. RESULTS: Based on measurements conducted on our tongue tracking system with a small magnetic tracer (diameter: 6.05 mm, thickness: 1.25 mm, residual induction: 14 800 G), the JCL algorithm achieves averaged root mean square error of 0.45 mm for tracer position estimation and for tracer orientation estimation, which are significantly lower than those of the separate calibration and localization algorithms. CONCLUSION: These results show that JCL can help improve the localization accuracy of this system. SIGNIFICANCE: A potentially high precision tongue tracking method is demonstrated.
BACKGROUND: Tongue tracking, which helps researchers gain valuable insights into speech mechanism, has many applications in speech therapy and language learning. The wireless localization technique, which involves tracking a small magnetic tracer within the 3-D oral space, provides a low cost and convenient approach to capture tongue kinematics. In practice, this technique requires accurate calibration of three-axial magnetic sensors used in the tracking system. The data-driven calibration depends on the trajectories of magnetic tracer and the ambient noise, which may change across time and space. METHODS: In this paper, we model the kinematics of tracer movement and the noisy magnetic measurements in a Bayesian framework, then present a joint calibration and localization (JCL) algorithm based on expectation maximization (EM), where the unscented Rauch-Tung-Striebel smoother is employed for tracer localization and the curvilinear search algorithm is applied for sensor calibration. RESULTS: Based on measurements conducted on our tongue tracking system with a small magnetic tracer (diameter: 6.05 mm, thickness: 1.25 mm, residual induction: 14 800 G), the JCL algorithm achieves averaged root mean square error of 0.45 mm for tracer position estimation and for tracer orientation estimation, which are significantly lower than those of the separate calibration and localization algorithms. CONCLUSION: These results show that JCL can help improve the localization accuracy of this system. SIGNIFICANCE: A potentially high precision tongue tracking method is demonstrated.
Authors: Yana Yunusova; Jordan R Green; Lauren Greenwood; Jun Wang; Gary L Pattee; Lorne Zinman Journal: Folia Phoniatr Logop Date: 2012-04-27 Impact factor: 0.849
Authors: Lianne Remijn; Gert Weijers; Maria W G Nijhuis-van der Sanden; Brenda E Groen; Chris L de Korte Journal: Ultrasound Med Biol Date: 2015-03-24 Impact factor: 2.998