In this community review report, we discuss applications and techniques for fast machine
learning (ML) in science—the concept of integrating powerful ML methods into the real-time …

Large-scale language models show promising text generation capabilities, but users cannot
easily control particular aspects of the generated text. We release CTRL, a 1.63 billion …

Quantization techniques can reduce the size of Deep Neural Networks and improve
inference latency and throughput by taking advantage of high throughput integer …

We propose a new end-to-end neural acoustic model for automatic speech recognition. The
model is composed of multiple blocks with residual connections between them. Each block …

For multilayer perceptron (MLP), the initial weights will significantly influence its
performance. Based on the enhanced fractional derivative extend from convex optimization …

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 …

We present a real-time neural radiance caching method for path-traced global illumination.
Our system is designed to handle fully dynamic scenes, and makes no assumptions about …

The last decade brought significant advances in automatic speech recognition (ASR) thanks
to the evolution of deep learning methods. ASR systems evolved from pipeline-based …

Background The development of deep learning (DL) models for prostate segmentation on
magnetic resonance imaging (MRI) depends on expert-annotated data and reliable …

We propose Citrinet-a new end-to-end convolutional Connectionist Temporal Classification
(CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural …