Most deep noise suppression (DNS) models are trained with reference-base...
The task of semantic segmentation requires a model to assign semantic la...
Deep neural networks (DNNs) have proven their capabilities in many areas...
Wideband codecs such as AMR-WB or EVS are widely used in (mobile) speech...
The powerful modeling capabilities of all-attention-based transformer
ar...
The emergence of data-driven machine learning (ML) has facilitated
signi...
Amodal perception terms the ability of humans to imagine the entire shap...
Although today's speech communication systems support various bandwidths...
Perceptual evaluation of speech quality (PESQ) requires a clean speech
r...
While deep neural networks (DNNs) achieve impressive performance on
envi...
Environment perception in autonomous driving vehicles often heavily reli...
In recent years, semantic segmentation has taken benefit from various wo...
Reconfigurable intelligent surface (RIS) is an emerging technology for f...
Speech enhancement employing deep neural networks (DNNs) for denoising a...
Scaling the distribution of automated vehicles requires handling various...
Recently, attention-based encoder-decoder (AED) models have shown high
p...
In this work we address the task of observing the performance of a seman...
A 360 perception of scene geometry is essential for automated driving,
n...
Stream fusion, also known as system combination, is a common technique i...
In recent years, deep neural networks (DNNs) were studied as an alternat...
Systems and functions that rely on machine learning (ML) are the basis o...
Automated driving has become a major topic of interest not only in the a...
Enabling autonomous driving (AD) can be considered one of the biggest
ch...
Despite recent advancements, deep neural networks are not robust against...
Deep neural networks are often not robust to semantically-irrelevant cha...
In this paper we present a solution to the task of "unsupervised domain
...
Deep neural networks tend to be vulnerable to adversarial perturbations,...
State-of-the-art self-supervised learning approaches for monocular depth...
Analyzing and predicting the traffic scene around the ego vehicle has be...
Self-supervised monocular depth estimation presents a powerful method to...
Autonomous driving requires self awareness of its perception functions.
...
While neural networks trained for semantic segmentation are essential fo...
While current approaches for neural network training often aim at improv...
Estimating time-frequency domain masks for single-channel speech enhance...
Single-channel speech enhancement with deep neural networks (DNNs) has s...
The progress in autonomous driving is also due to the increased availabi...
The high amount of sensors required for autonomous driving poses enormou...
Enhancing coded speech suffering from far-end acoustic background noise,...