Improving Ultrasound Tongue Image Reconstruction from Lip Images Using Self-supervised Learning and Attention Mechanism
This work addresses a domain-specific problem in speech production modeling, offering an incremental improvement by applying existing methods like self-supervised learning and attention to a new data context.
The paper tackles the problem of reconstructing ultrasound tongue images from lip image sequences using a self-supervised learning approach with attention mechanisms, achieving results that generate images close to real ultrasound tongue images and enable matching between imaging modalities.
Speech production is a dynamic procedure, which involved multi human organs including the tongue, jaw and lips. Modeling the dynamics of the vocal tract deformation is a fundamental problem to understand the speech, which is the most common way for human daily communication. Researchers employ several sensory streams to describe the process simultaneously, which are incontrovertibly statistically related to other streams. In this paper, we address the following question: given an observable image sequences of lips, can we picture the corresponding tongue motion. We formulated this problem as the self-supervised learning problem, and employ the two-stream convolutional network and long-short memory network for the learning task, with the attention mechanism. We evaluate the performance of the proposed method by leveraging the unlabeled lip videos to predict an upcoming ultrasound tongue image sequence. The results show that our model is able to generate images that close to the real ultrasound tongue images, and results in the matching between two imaging modalities.