Search Results for author:
Found 46 papers, 15 papers with code
Efficient High-Performance Bark-Scale Neural Network for Residual Echo and Noise Suppression
In recent years, the introduction of neural networks (NNs) into the field of speech enhancement has brought significant improvements.
Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation
In a second step, we train a generalizing model by adapting towards this pseudo-target domain.
Employing Real Training Data for Deep Noise Suppression
It provides a reference-free perceptual loss for employing real data during DNS training, maximizing the PESQ scores.
A Re-Parameterized Vision Transformer (ReVT) for Domain-Generalized Semantic Segmentation
We present a new augmentation-driven approach to domain generalization for semantic segmentation using a re-parameterized vision transformer (ReVT) with weight averaging of multiple models after training.
Efficient Acoustic Echo Suppression with Condition-Aware Training
The topic of deep acoustic echo control (DAEC) has seen many approaches with various model topologies in recent years.
DNN-Based Map Deviation Detection in LiDAR Point Clouds
In this work we present a novel deep learning-based approach to detect and specify map deviations in erroneous or outdated high-definition (HD) maps using both sensor and map data as input to a deep neural network (DNN).
EffCRN: An Efficient Convolutional Recurrent Network for High-Performance Speech Enhancement
By applying a number of topological changes at once, we propose both an efficient FCRN (FCRN15), and a new family of efficient convolutional recurrent neural networks (EffCRN23, EffCRN23lite).
Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving
DNNs play a significant role in environment perception for the challenging application of automated driving and are employed for tasks such as detection, semantic segmentation, and sensor fusion.
Coded Speech Quality Measurement by a Non-Intrusive PESQ-DNN
We illustrate the potential of this model by predicting the PESQ scores of wideband-coded speech obtained from AMR-WB or EVS codecs operating at different bitrates in noisy, tandeming, and error-prone transmission conditions.
Relaxed Attention for Transformer Models
The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive transformer decoder complicating the integration of external language models.
Ranked #3 on
Lipreading
on LRS3-TED
(using extra training data)
Amodal Cityscapes: A New Dataset, its Generation, and an Amodal Semantic Segmentation Challenge Baseline
In this paper, we consider the task of amodal semantic segmentation and propose a generic way to generate datasets to train amodal semantic segmentation methods.
On the Choice of Data for Efficient Training and Validation of End-to-End Driving Models
The emergence of data-driven machine learning (ML) has facilitated significant progress in many complicated tasks such as highly-automated driving.
Bandwidth-Scalable Fully Mask-Based Deep FCRN Acoustic Echo Cancellation and Postfiltering
Although today's speech communication systems support various bandwidths from narrowband to super-wideband and beyond, state-of-the art DNN methods for acoustic echo cancellation (AEC) are lacking modularity and bandwidth scalability.
Does a PESQNet (Loss) Require a Clean Reference Input? The Original PESQ Does, But ACR Listening Tests Don't
Detailed analyses show that the DNS trained with the MF-intrusive PESQNet outperforms the Interspeech 2021 DNS Challenge baseline and the same DNS trained with an MSE loss by 0. 23 and 0. 12 PESQ points, respectively.
Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation
In this work, we further expand a source-free UDA approach to a continual and therefore online-capable UDA on a single-image basis for semantic segmentation.
Detecting Adversarial Perturbations in Multi-Task Perception
In this paper, we (i) propose a novel adversarial perturbation detection scheme based on multi-task perception of complex vision tasks (i. e., depth estimation and semantic segmentation).
Improving Performance of Semantic Segmentation CycleGANs by Noise Injection into the Latent Segmentation Space
The proposed methodology allows to achieve an mIoU improvement on the Cityscapes validation set of 5. 7% absolute over the same CycleGAN without noise injection, and still an absolute 4. 9% over the ERFNet non-cyclic baseline.
Reconfigurable Intelligent Surface Enabled Spatial Multiplexing with Fully Convolutional Network
The rectangular shape of the RIS and the spatial correlation of channels with adjacent RIS antennas due to the short distance between them encourage us to apply it for the RIS configuration.
Deep Noise Suppression Maximizing Non-Differentiable PESQ Mediated by a Non-Intrusive PESQNet
Perceptual evaluation of speech quality (PESQ) is a widely used metric for evaluating speech quality.
Description of Corner Cases in Automated Driving: Goals and Challenges
Scaling the distribution of automated vehicles requires handling various unexpected and possibly dangerous situations, termed corner cases (CC).
Deep Residual Echo Suppression and Noise Reduction: A Multi-Input FCRN Approach in a Hybrid Speech Enhancement System
Deep neural network (DNN)-based approaches to acoustic echo cancellation (AEC) and hybrid speech enhancement systems have gained increasing attention recently, introducing significant performance improvements to this research field.
Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition
Recently, attention-based encoder-decoder (AED) models have shown high performance for end-to-end automatic speech recognition (ASR) across several tasks.
Ranked #7 on
Speech Recognition
on WSJ eval92
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
Our paper addresses both machine learning experts and safety engineers: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods.
Improving Online Performance Prediction for Semantic Segmentation
In this work we address the task of observing the performance of a semantic segmentation deep neural network (DNN) during online operation, i. e., during inference, which is of high importance in safety-critical applications such as autonomous driving.
SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras
We evaluate our approach on the Fisheye WoodScape surround-view dataset, significantly improving over previous approaches.
Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition
Stream fusion, also known as system combination, is a common technique in automatic speech recognition for traditional hybrid hidden Markov model approaches, yet mostly unexplored for modern deep neural network end-to-end model architectures.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Y$^2$-Net FCRN for Acoustic Echo and Noise Suppression
The proposed models achieved remarkable performance for the separate tasks of AEC and residual echo suppression (RES).
Deep Noise Suppression With Non-Intrusive PESQNet Supervision Enabling the Use of Real Training Data
During the training process, most of the speech enhancement neural networks are trained in a fully supervised way with losses requiring noisy speech to be synthesized by clean speech and additive noise.
AEC in a NetShell: On Target and Topology Choices for FCRN Acoustic Echo Cancellation
Acoustic echo cancellation (AEC) algorithms have a long-term steady role in signal processing, with approaches improving the performance of applications such as automotive hands-free systems, smart home and loudspeaker devices, or web conference systems.
An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving
Systems and functions that rely on machine learning (ML) are the basis of highly automated driving.
Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches
Hence, their detection is highly safety-critical, and detection methods can be applied to vast amounts of collected data to select suitable training data.
The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing
Although CNNs obtain state-of-the-art performance on clean images, almost imperceptible changes to the input, referred to as adversarial perturbations, may lead to fatal deception.
A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs
Deep neural networks are often not robust to semantically-irrelevant changes in the input.
From a Fourier-Domain Perspective on Adversarial Examples to a Wiener Filter Defense for Semantic Segmentation
Despite recent advancements, deep neural networks are not robust against adversarial perturbations.
Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method for Semantic Segmentation Without Using Source Domain Representations
In this paper we present a solution to the task of "unsupervised domain adaptation (UDA) of a given pre-trained semantic segmentation model without relying on any source domain representations".
Transferable Universal Adversarial Perturbations Using Generative Models
Using our generated non-targeted UAPs, we obtain an average fooling rate of 93. 36% on the source models (state of the art: 82. 16%).
SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Driving
This paper introduces a novel multi-task learning strategy to improve self-supervised monocular distance estimation on fisheye and pinhole camera images.
openDD: A Large-Scale Roundabout Drone Dataset
Analyzing and predicting the traffic scene around the ego vehicle has been one of the key challenges in autonomous driving.
Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance
Self-supervised monocular depth estimation presents a powerful method to obtain 3D scene information from single camera images, which is trainable on arbitrary image sequences without requiring depth labels, e. g., from a LiDAR sensor.
Self-Supervised Domain Mismatch Estimation for Autonomous Perception
Autonomous driving requires self awareness of its perception functions.
Class-Incremental Learning for Semantic Segmentation Re-Using Neither Old Data Nor Old Labels
While neural networks trained for semantic segmentation are essential for perception in autonomous driving, most current algorithms assume a fixed number of classes, presenting a major limitation when developing new autonomous driving systems with the need of additional classes.
Improved Noise and Attack Robustness for Semantic Segmentation by Using Multi-Task Training with Self-Supervised Depth Estimation
We show the effectiveness of our method on the Cityscapes dataset, where our multi-task training approach consistently outperforms the single-task semantic segmentation baseline in terms of both robustness vs. noise and in terms of adversarial attacks, without the need for depth labels in training.
A Perceptual Weighting Filter Loss for DNN Training in Speech Enhancement
Single-channel speech enhancement with deep neural networks (DNNs) has shown promising performance and is thus intensively being studied.
Towards Corner Case Detection for Autonomous Driving
The progress in autonomous driving is also due to the increased availability of vast amounts of training data for the underlying machine learning approaches.
GAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation
The high amount of sensors required for autonomous driving poses enormous challenges on the capacity of automotive bus systems.
Convolutional Neural Networks to Enhance Coded Speech
Enhancing coded speech suffering from far-end acoustic background noise, quantization noise, and potentially transmission errors, is a challenging task.
