Model-based inverse estimation for active contraction stresses of tongue muscles using 3D surface shape in speech production

Tongue model construction based on ultrasound images with image processing and deep learning method

PURPOSE

The purpose of this paper is to construct a 3D tongue model and to generate an animation of tongue movement for speech therapy in patients with lateral articulation (LA).

METHODS

The 3D tongue model is generated based on ultrasound (US) images, which are widely used in many clinics. A tongue model is constructed by extracting the tongue surfaces from US images with the help of image processing techniques and a deep learning method. A reference tongue model is generated first using US images of a normal speaker, and a model of an LA patient is then constructed by modifying the reference tongue model. An animation of the tongue movement is generated by deforming the model according to a time sequence.

RESULTS

The accuracy of the tongue surfaces estimated by a deep learning method were 22/45 = 49% and 29/45 = 64% for US images of a normal speaker and an LA patient, respectively. In addition, the maximum vertical errors between the ground truth and the estimated spline curves were 1.01 and 1.03 mm for US images of a normal speaker and an LA patient, respectively.

CONCLUSION

We have constructed a tongue model and generated a tongue movement animation of an LA patient using US images. The maximum vertical error between the ground truth and the estimated spline curves was only 1.03 mm, and we have confirmed that the generated tongue model is very useful for speech therapy in LA patients.

Frequent Karaoke Training Improves Frontal Executive Cognitive Skills, Tongue Pressure, and Respiratory Function in Elderly People: Pilot Study from a Randomized Controlled Trial

We tested whether karaoke training improves cognitive skills and reduces the risk of physical function impairments. We conducted a single-blinded randomized controlled trial in 26 elderly participants at residential care facilities, who were generally healthy or required the lowest level of care. Participants were near the threshold for mild cognitive impairment with the Montreal Cognitive Assessment (MoCA) and close to the sarcopenia cut-off with the skeletal muscle mass index. Pulmonary function as measured with spirometry and tongue strength were used as markers for physical functions affected by sarcopenia. Karaoke training occurred once a week for two hours, with an hour of homework assigned weekly. Karaoke training significantly improved the Frontal Assessment Battery at bedside (FAB) compared with an active control group receiving scratch art training (F = 8.04, permutation p-value = 0.013). Subscore improved with inhibitory control (F = 7.63, permutation p-value = 0.015) and sensitivity to interference (F = 11.98, permutation p-value = 0.001). We observed improved tongue pressure (F = 4.49, permutation p-value = 0.040) and pulmonary function by a greater increase in FIV1 (F = 5.22, permutation p-value = 0.047). Engaging elderly people, especially those in care homes, with karaoke training exercises that are moderately physically challenging may be a key to slowing cognitive decline and preventing dysphagia by sarcopenia.