检索结果-内蒙古大学图书馆

CMGAN: Conformer-based Metric GAN for Speech Enhancement

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cao, Ruizhe Abdulatif, Sherif Yang, Bin University of Stuttgart Institute of Signal Processing and System Theory Stuttgart Germany

Recently, convolution-augmented transformer (Conformer) has achieved promising performance in automatic speech recognition (ASR) and time-domain speech enhancement (SE), as it can capture both local and global dependencies in the speech signal. In this paper, we propose a conformer-based metric generative adversarial network (CMGAN) for SE in the time-frequency (TF) domain. In the generator, we utilize two-stage conformer blocks to aggregate all magnitude and complex spectrogram information by modeling both time and frequency dependencies. The estimation of magnitude and complex spectrogram is decoupled in the decoder stage and then jointly incorporated to reconstruct the enhanced speech. In addition, a metric discriminator is employed to further improve the quality of the enhanced estimated speech by optimizing the generator with respect to a corresponding evaluation score. Quantitative analysis on Voice Bank+DEMAND dataset indicates the capability of CMGAN in outperforming various previous models with a margin, i.e., PESQ of 3.41 and SSNR of 11.10 dB. Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

SELD-TCN: Sound event localization & detection via temporal convolutional networks 28

学校读者我要写书评

暂无评论

SELD-TCN: Sound event localization & detection via temporal ...

28th European Signal Processing Conference, EUSIPCO 2020

作者： Guirguis, Karim Schorn, Christoph Guntoro, Andre Abdulatif, Sherif Yang, Bin Robert Bosch GmbH Renningen Germany University of Stuttgart Institute of Signal Processing and System Theory Stuttgart Germany

ISBN: (纸本)9789082797053

The understanding of the surrounding environment plays a critical role in autonomous robotic systems, such as self-driving cars. Extensive research has been carried out concerning visual perception. Yet, to obtain a more complete perception of the environment, autonomous systems of the future should also take acoustic information into account. Recent sound event localization and detection (SELD) frameworks utilize convolutional recurrent neural networks (CRNNs). However, considering the recurrent nature of CRNNs, it becomes challenging to implement them efficiently on embedded hardware. Not only are their computations strenuous to parallelize, but they also require high memory bandwidth and large memory buffers. In this work, we develop a more robust and hardware-friendly novel architecture based on a temporal convolutional network (TCN). The proposed framework (SELD-TCN) outperforms the state-of-the-art SELDnet performance on four different datasets. Moreover, SELD-TCN achieves 4x faster training time per epoch and 40x faster inference time on an ordinary graphics processing unit (GPU). © 2021 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Recurrent neural networks

Continual Unsupervised Domain Adaptation for Semantic Segmentation using a Class-Specific Transfer

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Marsden, Robert A. F., Wiewel M., Döbler Y., Yang B., Yang Institute of Signal Processing and System Theory University of Stuttgart Stuttgart Germany

In recent years, there has been tremendous progress in the field of semantic image segmentation. However, one remaining challenging problem is that segmentation models do not generalize to unseen domains. To overcome this problem, one either has to label lots of data covering the whole variety of possible domains, which is often infeasible in practice, or apply unsupervised domain adaptation (UDA), only requiring labeled source data. In this work, we focus on UDA and additionally address the case of adapting not only to a single domain, but to a sequence of target domains. This requires mechanisms preventing the model from forgetting its previously learned knowledge. To adapt a segmentation model to a target domain, we follow the idea of utilizing light-weight style transfer to convert the style of labeled source images into the style of the target domain, while retaining the source content. To mitigate the distributional shift between the source and the target domain, the model is fine-tuned on the transferred source images in a second step. Existing lightweight style transfer approaches relying on adaptive instance normalization (AdaIN) or Fourier transformation (FDA) still lack performance and do not substantially improve upon common data augmentation, such as color jittering. The reason for this is that these methods do not focus on region- or class-specific differences, but mainly capture the most salient style. Therefore, we propose a simple and light-weight framework that incorporates two class-conditional AdaIN layers. To extract the class-specific target moments needed for the transfer layers, we use unfiltered pseudo-labels, which we show to be an effective approximation compared to real labels. We extensively validate our approach (CACE) on a synthetic sequence and further propose a challenging sequence consisting of real domains. CACE outperforms existing methods visually and quantitatively. © 2022, CC BY.

关键词： Semantic Segmentation

Simplified modeling of electromagnets for dynamic simulation of transient effects for a synchronous electric motor

学校读者我要写书评

暂无评论

International Journal of Mechanical system Dynamics 2021年第1期1卷 89-95页

作者： Florian Bechler Julius Kesten Florian Wittemann Frank Henning Martin Doppelbauer Peter Eberhard Institute of Engineering and Computational Mechanics University of StuttgartStuttgartGermany Institute of Electrical Engineering Karlsruhe Institute of Technology(KIT)KarlsruheGermany Institute of Vehicle System Technology Karlsruhe Institute of Technology(KIT)KarlsruheGermany

This study aims to show an approach for the dynamic simulation of a synchro-nous *** magnetic forces in the air gap are calculated efficiently using simplified approaches without neglecting important *** the modeling of the magnetic forces,an equivalent magnetic circuit is constructed in which the magnetic saturation and the leakage flux are taken into account and coupled with the electrical circuit at the *** calculated magnetic forces are then passed to a mechanical model of the *** with a predefinable load torque,the resulting motor rotation and the forces in the bearings are *** presented model is then investigated in a small *** novel ap-proach is intended to provide a method of calculating dynamically the forces transmitted from the shaft to the motor housing and to create the basis for evaluating electric motors for vibrations,noise,and harshness under varying loads and input voltages.

关键词： dynamic simulation electromagnet electromagnet modeling magnetomotive forces

Recursive Feasibility and Stability for Stochastic MPC based on Polynomial Chaos

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2023年第1期56卷 204-209页

作者： Zhiming Ma Henning Schlüter Felix Berkel Thomas Specker Frank Allgöwer Faculty for Engineering Design Production Engineering and Automotive Engineering University of Stuttgart 70550 Stuttgart Germany Corporate Research Robert Bosch GmbH 71272 Renningen Germany Institute for Systems Theory and Automatic Control University of Stuttgart 70550 Stuttgart Germany

This paper deals with stochastic model predictive control (SMPC) based on polynomial chaos expansion (PCE) for linear systems with time-invariant stochastic parametric uncertainties and time-varying stochastic additive disturbances subject to chance constraints on states and inputs. Exploiting terminal ingredients in the SMPC problem and a hybrid update strategy, a recursively feasible optimization problem is formulated. Moreover, stability of the system of PCE coefficients can be shown. Furthermore, in the paper the performance and computational complexity of SMPC based on PCEs is compared to tube-based SMPC and robust model predictive control (RMPC) is analyzed and benefits are demonstrated in simulation.

关键词： Model predictive control stochastic control polynomial chaos expansion

Switching Control for Load Sway Suppression of a Rotary Crane Using Only Horizontal Boom Motion

学校读者我要写书评

暂无评论

Switching Control for Load Sway Suppression of a Rotary Cran...

International Workshop on Variable Structure systems, VSS

作者： Katrina Hurter Frank Wolff Oliver Sawodny Naoki Uchiyama Institute for System Dynamics University of Stuttgart Stuttgart Germany Department of Mechanical Engineering Toyohashi University of Technology Toyohashi Aichi Japan

ISBN: (数字)9798350353686

ISBN: (纸本)9798350353693

The paper deals with automatic load sway reduction for boom cranes, an increasingly important topic in the field due to its use towards increased productivity and safety. Boom cranes are a type of rotary crane, where the load is suspended by a rope from the tip of a boom based at the crane centre. This allows for vertical movement by adjusting the inclination of the boom, and horizontal movement through rotation around the base of the boom. In most research, both vertical and horizontal boom motion are used to control load sway. However, the vertical motion expends more energy as it moves against gravity. Our task is to use only the horizontal motion to perform positioning of the boom and load sway reduction in two directions, thus reducing energy cost. In order to achieve this, a new two mode switching controller is developed, which uses logical arguments to switch between goal-specific modes. Mode 1 focuses on the correct positioning of the boom through the use of a trajectory and a linear quadratic controller, Mode 2 focuses on load sway reduction through the use of a linear quadratic controller. Two different approaches for scheduling the switching times between the modes are developed. The resulting controller is successfully verified both in simulation and experiments on a laboratory crane.

关键词： Variable structure systems Productivity Cranes Costs Switches Control systems Trajectory Safety Feedback control Gravity

TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bartler, Alexander Bender, Florian Wiewel, Felix Yang, Bin Institute of Signal Processing and System Theory University of Stuttgart Stuttgart Germany

Nowadays, deep neural networks outperform humans in many tasks. However, if the input distribution drifts away from the one used in training, their performance drops significantly. Recently published research has shown that adapting the model parameters to the test sample can mitigate this performance degradation. In this paper, we therefore propose a novel modification of the self-supervised training algorithm SwAV that adds the ability to adapt to single test samples. Using the provided prototypes of SwAV and our derived test-time loss, we align the representation of unseen test samples with the self-supervised learned prototypes. We show the success of our method on the common benchmark dataset CIFAR10-C. © 2022, CC BY.

关键词： Deep neural networks

Exploring Domain Shift on Radar-Based 3D Object Detection Amidst Diverse Environmental Conditions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Miao Abdulatif, Sherif Loesch, Benedikt Altmann, Marco Schwarz, Marius Yang, Bin Robert Bosch GmbH Corporate Research 71272 Germany University of Stuttgart Institute of Signal Processing and System Theory 70569 Germany

The rapid evolution of deep learning and its integration with autonomous driving systems have led to substantial advancements in 3D perception using multimodal sensors. Notably, radar sensors show greater robustness compared to cameras and lidar under adverse weather and varying illumination conditions. This study delves into the often-overlooked yet crucial issue of domain shift in 4D radar-based object detection, examining how varying environmental conditions, such as different weather patterns and road types, impact 3D object detection performance. Our findings highlight distinct domain shifts across various weather scenarios, revealing unique dataset sensitivities that underscore the critical role of radar point cloud generation. Additionally, we demonstrate that transitioning between different road types, especially from highways to urban settings, introduces notable domain shifts, emphasizing the necessity for diverse data collection across varied road environments. To the best of our knowledge, this is the first comprehensive analysis of domain shift effects on 4D radar-based object detection. We believe this empirical study contributes to understanding the complex nature of domain shifts in radar data and suggests paths forward for data collection strategy in the face of environmental variability. Copyright © 2024, The Authors. All rights reserved.

关键词： Network security

A Joint Optimization Policy of Tail Assignment and Maintenance Scheme for Civil Aircraft Fleet 14

学校读者我要写书评

暂无评论

A Joint Optimization Policy of Tail Assignment and Maintenan...

14th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Hangzhou 2023

作者： Ding, Yutong Zhang, Kaigan Wang, Yu Xu, Yuhui Zhu, Ying Xia, Tangbin Xi, Lifeng Seidelmann, Joachim State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University SJTU-Fraunhofer Center Shanghai China Fraunhofer Institute for Manufacturing Engineering and Automation Stuttgart Germany

ISBN: (纸本)9798350301359

This study aims to improve the collaborative administration of operations and maintenance for civil aircraft fleet. To overcome the challenge of simultaneously considering the flight path and maintenance requirement, a modified connection network framework is developed by innovatively introducing the maintenance opportunity node. Based on the network construction, an integer programming model is formulated for the collaborative optimization of tail assignment and maintenance scheduling. To tackle the large scale of this problem, a problem decomposition-based two-stage solution process is presented, which is composed of the maintenance opportunity-oriented tail assignment optimization and the reasonable maintenance task allocation procedure. Compared to the traditional manually scheduled letter check mode, our work could efficiently output the cost-effective joint scheme of tail assignment and maintenance task allocation for airlines. © 2023 IEEE.

关键词： aircraft fleet airline network modeling constuctive heuristic maintenance scheduling tail assignment