Dilated Convolutional Neural Network for Tongue Segmentation in Real-time Ultrasound Video Data

Mohammad Hamed Mozaffari, Won-Sook Lee

Abstract: The progress of deep convolutional neural networks has been successfully exploited in various real-time computer vision tasks such as image classification and segmentation. Owing to the development of computational units, availability of digital datasets, and improved performance of deep learning models, fully automatic and accurate tracking of tongue contours in real-time ultrasound data became practical only in recent years. Previous studies have shown that the performance of deep learning techniques is significant in tracking ultrasound tongue contours in real-time applications such as pronunciation training using multimodal ultrasound-enhanced approaches. In this paper, we investigated the performance of a novel convolutional neural network inspired by the peripheral vision ability of the human eye (named IrisNet) in tongue contour tracking tasks. Qualitative and quantitative assessment of IrisNet on different ultrasound tongue datasets revealed its outstanding generalization ability of the network compared with similar techniques.