Large audio tagging models are usually trained or pre-trained on AudioSet, a dataset that encompasses a large amount of different sound classes and acoustic environments. Knowledge distillation has emerged as a method to compress such models without compromising their...
Today’s generative neural networks allow the creation of high-quality synthetic speech at scale. While we welcome the creative use of this new technology, we must also recognize the risks. As synthetic speech is abused for monetary and identity theft, we require a...
The fast wavelet transform is an important workhorse in signal processing. Wavelets are local in the spatial- or temporal- and the frequency-domain. This property enables frequency domain analysis while preserving some spatiotemporal information. Until recently,...
Neural radiance-density field methods have become increasingly popular for the task of novel-view rendering. Their recent extension to hash-based positional encoding ensures fast training and inference with visually pleasing results. However, density-based methods...
Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set size, model size, and compute, which offers valuable guidance as large-scale experiments...
We present an approach for estimating a mobile robot’s pose w.r.t. the allocentric coordinates of a network of static cameras using multi-view RGB images. The images are processed online, locally on smart edge sensors by deep neural networks to detect the robot and...
