Ultrasound Tongue

Ultrasound tongue imaging (UTI) is emerging as a valuable tool for analyzing tongue movement and morphology, with applications spanning speech therapy, Traditional Chinese Medicine (TCM) diagnosis, and speech enhancement. Current research focuses on developing automated methods for UTI analysis using deep learning models, including convolutional neural networks (CNNs), vision transformers (ViTs), and diffusion models, often incorporating multi-task learning and knowledge distillation techniques to improve accuracy and efficiency. These advancements hold significant promise for improving the objectivity and accuracy of diagnoses related to speech disorders, TCM tongue assessment, and ultimately, for enhancing the understanding of human speech production and its associated pathologies.