Automatically assessing emotional valence in human speech has historically been a difficult task for machine learning algorithms. The subtle changes in the voice of the speaker that are indicative of positive or negative emotional states are often "overshadowed" by voice characteristics relating to emotional intensity or emotional activation. In this work we explore a representation learning approach that automatically derives discriminative representations of emotional speech. In particular, we investigate two machine learning strategies to improve classifier performance: (1) utilization of unlabeled data using a deep convolutional generative adversarial network (DCGAN), and (2) multitask learning. Within our extensive experiments we leverage a multitask annotated emotional corpus as well as a large unlabeled meeting corpus (around 100 hours). Our speakerindependent classification experiments show that in particular the use of unlabeled data in our investigations improves performance of the classifiers and both fully supervised baseline approaches are outperformed considerably. We improve the classification of emotional valence on a discrete 5-point scale to 43.88% and on a 3-point scale to 49.80%, which is competitive to state-of-the-art performance.

Hair exhibits strong anisotropic dynamic properties which demand distinct dynamic models for single strands and hair-hair interactions. While a single strand can be modeled as a multibody open chain expressed in generalized coordinates, modeling hair-hair interactions is a more difficult problem. A dynamic model for this purpose is proposed based on a sparse set of guide strands. Long range connections among the strands are modeled as breakable static links formulated as nonreversible positional springs. Dynamic hair-to-hair collision is solved with the help of auxiliary triangle strips among nearby strands. Adaptive guide strands can be generated and removed on the fly to dynamically control the accuracy of a simulation. A high-quality dense hair model can be obtained at the end by transforming and interpolating the sparse guide strands. Fine imagery of the final dense model is rendered by considering both primary scattering and self-shadowing inside the hair volume which is modeled as being partially translucent.

No abstract

Facial surface symmetry, which is poorly assessed subjectively, can be easily and reproducibly measured using three-dimensional photogrammetry. The RMSD for facial asymmetry of healthy volunteers clusters at approximately 0.80 ± 0.24 mm. Patients with facial asymmetry due to a pathologic process can be differentiated from normative facial asymmetry based on their RMSDs.

No abstract