Current 2D face recognition systems encounter difficulties in recognizing faces with large pose variations. Utilizing the pose-invariant features of 3D face data has the potentia...
This paper investigates unsupervised vocabulary and language model self-adaptation (VLA) from just one speech file using the web as a knowledge source and without prior knowledge...
Varying channel conditions present a difficult problem for many speech technologies such as language identification (LID). Channel compensation techniques have been shown to sig...
The EuroMISE Center focuses on new approaches in the field of electronic health record (EHR). Among others, the structured health documentation in dentistry in the form of an EHR i...
We introduce a novel approach to modeling the dynamics of human facial motion induced by the action of speech for the purpose of synthesis. We represent the trajectories of a numbe...