In this paper we report state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data.Our model, Jasper, uses only 1D convolutions, batch normalization, ReLU, dropout, and residual connections.To improve training, we further introduce a new layer-wise optimizer called NovoGrad.Through experiments, we demonstrate that the proposed deep architecture performs as well or better than more complex choices.Our deepest Jasper variant uses 54 convolutional layers.With this architecture, we achieve 2.95% WER using a beam-search decoder with an external neural language model and 3.86% WER with a greedy decoder on LibriSpeech test-clean.We also report competitive results on Wall Street Journal and the Hub5'00 conversational evaluation datasets.

We describe an interactive system featuring fluid-driven animation that responds to moving objects. Our system includes a GPU-accelerated Eulerian fluid solver that is suited for real-time use because it is unconditionally stable, takes constant calculation time per frame, and provides good visual fidelity. We dynamically translate the fluid simulation domain to track a user-controlled object. The fluid motion is visualized via its effects on particles which respond to the calculated fluid velocity field, but which are not constrained to stay within the bounds of the simulation domain. As particles leave the simulation domain, they seamlessly transition to purely particle-based motion, obscuring the point at which the fluid simulation ends. We additionally describe a hardware-accelerated volume rendering system that treats the particles as participating media and can render effects such as smoke, dust, or mist. Taken together, these components can be used to add fluid-driven effects to an interactive system without enforcing constraints on user motion, and without visual artifacts resulting from the finite extents of Eulerian fluid simulation methods.

It is usually difficult to resolve the fine details of turbulent flows, especially when targeting real-time applications. We present a novel, scalable turbulence method that uses a realistic energy model and an efficient particle representation that allows for the accurate and robust simulation of small-scale detail. We compute transport of turbulent energy using a complete two-equation k -ε model with accurate production terms that allows us to capture anisotropic turbulence effects, which integrate smoothly into the base flow. We only require a very low grid resolution to resolve the underlying base flow. As we offload complexity from the fluid solver to the particle system, we can control the detail of the simulation easily by adjusting the number of particles, without changing the large scale behavior. In addition, no computations are wasted on areas that are not visible. We demonstrate that due to the design of our algorithm it is highly suitable for massively parallel architectures, and is able to generate detailed turbulent simulations with millions of particles at high framerates.

No abstract available.

The ability to specify non planar 3D curves is of fundamental importance in 3D modelling and animation systems. Effective techniques for specifying such curves using 2D input devices are desirable, but existing methods typically require the user to edit the curve from several viewpoints. We present a novel method for specifying 3D curves with 2D input from a single viewpoint. The user rst draws the curve as it appears from the current viewpoint, and then draws its shadow on the oor plane. The system correlates the curve with its shadow to compute the curve's 3D shape. This method is more natural than existing methods in that it leverages skills that many artists and designers have developed from work with pencil and paper.

We present a new particle-based surface representation with which a user can interactively sculpt free-form surfaces. The particles maintain mesh connectivity and operate under rules that lead them to form triangulations with properties that make them suitable for use in subdivision. A user interactively guides the particles, which we call skin, to grow over a given collection of polyhedral elements (or skeletons), yielding a smooth surface (through subdivision) that approximates the underlying skeletal shapes. Skin resembles blobby modeling in the constructive approach to modeling it supports, but allows a richer vocabulary of skeleton shapes, supports sharp creases where desired, and provides a convenient mechanism for adding multiresolution surface detail. CR