@inproceedings{24197, abstract = {{A monolithically integrated coherent receiver in silicon photonic technology is presented along with measurement results for constellation diagrams up to 64GBd and bandwidth of 34 GHz. To our knowledge this is the fastest single-chip coherent receiver.}}, author = {{Kress, Christian and Gudyriev, Sergiy and Zwickel, Heiner and Kemal, Juned N. and Lischke, Stefan and Zimmermann, Lars and Koos, Christian and Scheytt, Christoph}}, booktitle = {{Optical Fiber Communication Conference 2018, San Diego}}, location = {{San Diego, CA, USA }}, title = {{{64 GBd Monolithically Integrated Coherent QPSK Single Polarization Receiver in 0.25 µm SiGe-Photonic Technology}}}, volume = {{Th4A.6}}, year = {{2018}}, } @inproceedings{24189, author = {{Gudyriev, Sergiy and Kress, Christian and Scheytt, Christoph}}, booktitle = {{10th Sino-German Joint Symposium on Opto- and Microelectronic Devices and Circuits (SODC 2018)}}, publisher = {{IEEE}}, title = {{{Electronic Photonic Integrated Circuits for Coherent and Non-Coherent Receivers}}}, year = {{2018}}, } @inproceedings{24188, author = {{Scheytt, Christoph}}, booktitle = {{10th Sino-German Joint Symposium on Opto- and Microelectronic Devices and Circuits (SODC 2018)}}, publisher = {{IEEE}}, title = {{{Ultra‐broadband Signal Processing by means of Electronic‐Photonic Integration}}}, year = {{2018}}, } @inproceedings{24191, author = {{Gudyriev, Sergiy and Kress, Christian and Scheytt, Christoph}}, booktitle = {{DFG Priority Programme SPP2111}}, title = {{{Electronic‐Photonic Integrated Systems for Ultrafast Signal Processing}}}, year = {{2018}}, } @inproceedings{29923, abstract = {{This paper introduces a new open source platform for end-toend speech processing named ESPnet. ESPnet mainly focuses on end-to-end automatic speech recognition (ASR), and adopts widely-used dynamic neural network toolkits, Chainer and Py-Torch, as a main deep learning engine. ESPnet also follows the Kaldi ASR toolkit style for data processing, feature extraction/format, and recipes to provide a complete setup for speech recognition and other speech processing experiments. This paper explains a major architecture of this software platform, several important functionalities, which differentiate ESPnet from other open source ASR toolkits, and experimental results with major ASR benchmarks.}}, author = {{Watanabe, Shinji and Hori, Takaaki and Karita, Shigeki and Hayashi, Tomoki and Nishitoba, Jiro and Unno, Yuya and Enrique Yalta Soplin, Nelson and Heymann, Jahn and Wiesner, Matthew and Chen, Nanxin and Renduchintala, Adithya and Ochiai, Tsubasa}}, booktitle = {{INTERSPEECH 2018, Hyderabad, India}}, pages = {{2207–2211}}, title = {{{ESPnet: End-to-End Speech Processing Toolkit}}}, doi = {{10.21437/Interspeech.2018-1456}}, year = {{2018}}, } @inproceedings{48303, author = {{Habernal, Ivan and Wachsmuth, Henning and Gurevych, Iryna and Stein, Benno}}, booktitle = {{Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}}, publisher = {{Association for Computational Linguistics}}, title = {{{The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants}}}, doi = {{10.18653/v1/n18-1175}}, year = {{2018}}, } @inproceedings{48302, author = {{Habernal, Ivan and Wachsmuth, Henning and Gurevych, Iryna and Stein, Benno}}, booktitle = {{Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)}}, publisher = {{Association for Computational Linguistics}}, title = {{{Before Name-Calling: Dynamics and Triggers of Ad Hominem Fallacies in Web Argumentation}}}, doi = {{10.18653/v1/n18-1036}}, year = {{2018}}, } @inproceedings{48304, author = {{Daxenberger, Johannes and Eger, Steffen and Habernal, Ivan and Stab, Christian and Gurevych, Iryna}}, booktitle = {{Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing}}, publisher = {{Association for Computational Linguistics}}, title = {{{What is the Essence of a Claim? Cross-Domain Claim Identification}}}, doi = {{10.18653/v1/d17-1218}}, year = {{2018}}, } @inproceedings{12899, abstract = {{This contribution presents a speech enhancement system for the CHiME-5 Dinner Party Scenario. The front-end employs multi-channel linear time-variant filtering and achieves its gains without the use of a neural network. We present an adaptation of blind source separation techniques to the CHiME-5 database which we call Guided Source Separation (GSS). Using the baseline acoustic and language model, the combination of Weighted Prediction Error based dereverberation, guided source separation, and beamforming reduces the WER by 10:54% (relative) for the single array track and by 21:12% (relative) on the multiple array track.}}, author = {{Boeddeker, Christoph and Heitkaemper, Jens and Schmalenstroeer, Joerg and Drude, Lukas and Heymann, Jahn and Haeb-Umbach, Reinhold}}, booktitle = {{Proc. CHiME 2018 Workshop on Speech Processing in Everyday Environments, Hyderabad, India}}, title = {{{Front-End Processing for the CHiME-5 Dinner Party Scenario}}}, year = {{2018}}, } @inproceedings{6859, abstract = {{Signal processing in WASNs is based on a software framework for hosting the algorithms as well as on a set of wireless connected devices representing the hardware. Each of the nodes contributes memory, processing power, communication bandwidth and some sensor information for the tasks to be solved on the network. In this paper we present our MARVELO framework for distributed signal processing. It is intended for transforming existing centralized implementations into distributed versions. To this end, the software only needs a block-oriented implementation, which MARVELO picks-up and distributes on the network. Additionally, our sensor node hardware and the audio interfaces responsible for multi-channel recordings are presented.}}, author = {{Afifi, Haitham and Schmalenstroeer, Joerg and Ullmann, Joerg and Haeb-Umbach, Reinhold and Karl, Holger}}, booktitle = {{Speech Communication; 13th ITG-Symposium}}, pages = {{1--5}}, title = {{{MARVELO - A Framework for Signal Processing in Wireless Acoustic Sensor Networks}}}, year = {{2018}}, } @inproceedings{11747, abstract = {{In this paper, we present a neural network based classification algorithm for the discrimination of moving from stationary targets in the sight of an automotive radar sensor. Compared to existing algorithms, the proposed algorithm can take into account multiple local radar targets instead of performing classification inference on each target individually resulting in superior discrimination accuracy, especially suitable for non rigid objects, like pedestrians, which in general have a wide velocity spread when multiple targets are detected.}}, author = {{Grimm, Christopher and Breddermann, Tobias and Farhoud, Ridha and Fei, Tai and Warsitz, Ernst and Haeb-Umbach, Reinhold}}, booktitle = {{International Conference on Microwaves for Intelligent Mobility (ICMIM) 2018}}, title = {{{Discrimination of Stationary from Moving Targets with Recurrent Neural Networks in Automotive Radar}}}, year = {{2018}}, } @inproceedings{11907, abstract = {{The invention of the Variational Autoencoder enables the application of Neural Networks to a wide range of tasks in unsupervised learning, including the field of Acoustic Unit Discovery (AUD). The recently proposed Hidden Markov Model Variational Autoencoder (HMMVAE) allows a joint training of a neural network based feature extractor and a structured prior for the latent space given by a Hidden Markov Model. It has been shown that the HMMVAE significantly outperforms pure GMM-HMM based systems on the AUD task. However, the HMMVAE cannot autonomously infer the number of acoustic units and thus relies on the GMM-HMM system for initialization. This paper introduces the Bayesian Hidden Markov Model Variational Autoencoder (BHMMVAE) which solves these issues by embedding the HMMVAE in a Bayesian framework with a Dirichlet Process Prior for the distribution of the acoustic units, and diagonal or full-covariance Gaussians as emission distributions. Experiments on TIMIT and Xitsonga show that the BHMMVAE is able to autonomously infer a reasonable number of acoustic units, can be initialized without supervision by a GMM-HMM system, achieves computationally efficient stochastic variational inference by using natural gradient descent, and, additionally, improves the AUD performance over the HMMVAE.}}, author = {{Glarner, Thomas and Hanebrink, Patrick and Ebbers, Janek and Haeb-Umbach, Reinhold}}, booktitle = {{INTERSPEECH 2018, Hyderabad, India}}, title = {{{Full Bayesian Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery}}}, year = {{2018}}, } @inproceedings{46350, abstract = {{The ubiquity of WiFi access points and the sharp increase in WiFi-enabled devices carried by humans have paved the way for WiFi-based indoor positioning and location analysis. Locating people in indoor environments has numerous applications in robotics, crowd control, indoor facility optimization, and automated environment mapping. However, existing WiFi-based positioning systems suffer from two major problems: (1) their accuracy and precision is limited due to inherent noise induced by indoor obstacles, and (2) they only occasionally provide location estimates, namely when a WiFi-equipped device emits a signal. To mitigate these two issues, we propose a novel Gaussian process (GP) model for WiFi signal strength measurements. It allows for simultaneous smoothing (increasing accuracy and precision of estimators) and interpolation (enabling continuous sampling of location estimates). Furthermore, simple and efficient smoothing methods for location estimates are introduced to improve localization performance in real-time settings. Experiments are conducted on two data sets from a large real-world commercial indoor retail environment. Results demonstrate that our approach provides significant improvements in terms of precision and accuracy with respect to unfiltered data. Ultimately, the GP model realizes continuous location sampling with consistently high quality location estimates.}}, author = {{van Engelen, J.E. and van Lier, J.J. and Takes, F.W. and Trautmann, Heike}}, booktitle = {{Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Database (ECML/PKDD)}}, pages = {{524–540}}, publisher = {{Springer}}, title = {{{Accurate WiFi based indoor positioning with continuous location sampling}}}, year = {{2018}}, } @article{46351, abstract = {{Clustering is an important field in data mining that aims to reveal hidden patterns in data sets. It is widely popular in marketing or medical applications and used to identify groups of similar objects. Clustering possibly unbounded and evolving data streams is of particular interest due to the widespread deployment of large and fast data sources such as sensors. The vast majority of stream clustering algorithms employ a two-phase approach where the stream is first summarized in an online phase. Upon request, an offline phase reclusters the aggregations into the final clusters. In this setup, the online component will idle and wait for the next observation in times where the stream is slow. This paper proposes a new stream clustering algorithm called evoStream which performs evolutionary optimization in the idle times of the online phase to incrementally build and refine the final clusters. Since the online phase would idle otherwise, our approach does not reduce the processing speed while effectively removing the computational overhead of the offline phase. In extensive experiments on real data streams we show that the proposed algorithm allows to output clusters of high quality at any time within the stream without the need for additional computational resources.}}, author = {{Carnein, Matthias and Trautmann, Heike}}, journal = {{Big Data Research}}, pages = {{101–111}}, title = {{{evoStream — Evolutionary Stream Clustering Utilizing Idle Times}}}, doi = {{10.1016/j.bdr.2018.05.005}}, volume = {{14}}, year = {{2018}}, } @article{46353, abstract = {{Incorporating decision makers' preferences is of great significance in multiobjective optimization. Target region-based multiobjective evolutionary algorithms (TMOEAs), aiming at a well-distributed subset of Pareto optimal solutions within the user-provided region(s), are extensively investigated in this paper. An empirical comparison is performed among three TMOEA instantiations: T-NSGA-II, T-SMS-EMOA and T-R2-EMOA. Experimental results show that T-SMS-EMOA has the best overall performance regarding the hypervolume indicator within the target region, while T-NSGA-II is the fastest algorithm. We also compare TMOEAs with other state-of-the-art preference-based approaches, i.e., DF-SMS-EMOA, RVEA, AS-EMOA and R-NSGA-II to show the advantages of TMOEAs. A case study in the mission planning of earth observation satellite is carried out to verify the capabilities of TMOEAs in the real-world application. Experimental results indicate that preferences can improve the searching ability of MOEAs, and TMOEAs can successfully find nondominated solutions preferred by the decision maker.}}, author = {{Li, L and Wang, Y and Trautmann, Heike and Jing, N and Emmerich, M}}, journal = {{Swarm and Evolutionary Computation}}, pages = {{196–215}}, title = {{{Multiobjective evolutionary algorithms based on target region preferences}}}, doi = {{10.1016/j.swevo.2018.02.006}}, volume = {{40}}, year = {{2018}}, } @inproceedings{11838, abstract = {{Distributed sensor data acquisition usually encompasses data sampling by the individual devices, where each of them has its own oscillator driving the local sampling process, resulting in slightly different sampling rates at the individual sensor nodes. Nevertheless, for certain downstream signal processing tasks it is important to compensate even for small sampling rate offsets. Aligning the sampling rates of oscillators which differ only by a few parts-per-million, is, however, challenging and quite different from traditional multirate signal processing tasks. In this paper we propose to transfer a precise but computationally demanding time domain approach, inspired by the Nyquist-Shannon sampling theorem, to an efficient frequency domain implementation. To this end a buffer control is employed which compensates for sampling offsets which are multiples of the sampling period, while a digital filter, realized by the wellknown Overlap-Save method, handles the fractional part of the sampling phase offset. With experiments on artificially misaligned data we investigate the parametrization, the efficiency, and the induced distortions of the proposed resampling method. It is shown that a favorable compromise between residual distortion and computational complexity is achieved, compared to other sampling rate offset compensation techniques.}}, author = {{Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{26th European Signal Processing Conference (EUSIPCO 2018)}}, title = {{{Efficient Sampling Rate Offset Compensation - An Overlap-Save Based Approach}}}, year = {{2018}}, } @inproceedings{11876, abstract = {{This paper describes the systems for the single-array track and the multiple-array track of the 5th CHiME Challenge. The final system is a combination of multiple systems, using Confusion Network Combination (CNC). The different systems presented here are utilizing different front-ends and training sets for a Bidirectional Long Short-Term Memory (BLSTM) Acoustic Model (AM). The front-end was replaced by enhancements provided by Paderborn University [1]. The back-end has been implemented using RASR [2] and RETURNN [3]. Additionally, a system combination including the hypothesis word graphs from the system of the submission [1] has been performed, which results in the final best system.}}, author = {{Kitza, Markus and Michel, Wilfried and Boeddeker, Christoph and Heitkaemper, Jens and Menne, Tobias and Schlüter, Ralf and Ney, Hermann and Schmalenstroeer, Joerg and Drude, Lukas and Heymann, Jahn and Haeb-Umbach, Reinhold}}, booktitle = {{Proc. CHiME 2018 Workshop on Speech Processing in Everyday Environments, Hyderabad, India}}, title = {{{The RWTH/UPB System Combination for the CHiME 2018 Workshop}}}, year = {{2018}}, } @inproceedings{11836, abstract = {{Due to their distributed nature wireless acoustic sensor networks offer great potential for improved signal acquisition, processing and classification for applications such as monitoring and surveillance, home automation, or hands-free telecommunication. To reduce the communication demand with a central server and to raise the privacy level it is desirable to perform processing at node level. The limited processing and memory capabilities on a sensor node, however, stand in contrast to the compute and memory intensive deep learning algorithms used in modern speech and audio processing. In this work, we perform benchmarking of commonly used convolutional and recurrent neural network architectures on a Raspberry Pi based acoustic sensor node. We show that it is possible to run medium-sized neural network topologies used for speech enhancement and speech recognition in real time. For acoustic event recognition, where predictions in a lower temporal resolution are sufficient, it is even possible to run current state-of-the-art deep convolutional models with a real-time-factor of 0:11.}}, author = {{Ebbers, Janek and Heitkaemper, Jens and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{ITG 2018, Oldenburg, Germany}}, title = {{{Benchmarking Neural Network Architectures for Acoustic Sensor Networks}}}, year = {{2018}}, } @inproceedings{11839, abstract = {{It has been experimentally verified that sampling rate offsets (SROs) between the input channels of an acoustic beamformer have a detrimental effect on the achievable SNR gains. In this paper we derive an analytic model to study the impact of SRO on the estimation of the spatial noise covariance matrix used in MVDR beamforming. It is shown that a perfect compensation of the SRO is impossible if the noise covariance matrix is estimated by time averaging, even if the SRO is perfectly known. The SRO should therefore be compensated for prior to beamformer coefficient estimation. We present a novel scheme where SRO compensation and beamforming closely interact, saving some computational effort compared to separate SRO adjustment followed by acoustic beamforming.}}, author = {{Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{ITG 2018, Oldenburg, Germany}}, title = {{{Insights into the Interplay of Sampling Rate Offsets and MVDR Beamforming}}}, year = {{2018}}, } @inproceedings{45392, author = {{Dröse, Jennifer}}, booktitle = {{Beiträge zum Mathematikunterricht 2018}}, pages = {{469--472}}, publisher = {{WTM}}, title = {{{Textaufgaben strategisch und sprachlich bewältigen lernen – Pilotstudie zur Wirksamkeit eines Förderkonzepts}}}, year = {{2018}}, }