We present FacET, a general-purpose framework to discover interpretable, spatio-temporal trends between two domains, that works even in the presence of dominant biases.

We propose a novel touchless multimodal person identification model using deep learning techniques by combining the gait and speech modalities.

In this study, we propose a novel multi-modal end-to-end neural approach for automated assessment of non-native English speakers' spontaneous speech using attention fusion.