@article{15741,
  abstract     = {{
In many cyber–physical systems, we encounter the problem of remote state estimation of geo- graphically distributed and remote physical processes. This paper studies the scheduling of sensor transmissions to estimate the states of multiple remote, dynamic processes. Information from the different sensors has to be transmitted to a central gateway over a wireless network for monitoring purposes, where typically fewer wireless channels are available than there are processes to be monitored. For effective estimation at the gateway, the sensors need to be scheduled appropriately, i.e., at each time instant one needs to decide which sensors have network access and which ones do not. To address this scheduling problem, we formulate an associated Markov decision process (MDP). This MDP is then solved using a Deep Q-Network, a recent deep reinforcement learning algorithm that is at once scalable and model-free. We compare our scheduling algorithm to popular scheduling algorithms such as round-robin and reduced-waiting-time, among others. Our algorithm is shown to significantly outperform these algorithms for many example scenario}},
  author       = {{Leong, Alex S. and Ramaswamy, Arunselvan and Quevedo, Daniel E. and Karl, Holger and Shi, Ling}},
  issn         = {{0005-1098}},
  journal      = {{Automatica}},
  title        = {{{Deep reinforcement learning for wireless sensor scheduling in cyber–physical systems}}},
  doi          = {{10.1016/j.automatica.2019.108759}},
  year         = {{2019}},
}

@inproceedings{15812,
  abstract     = {{Connectionist temporal classification (CTC) is a sequence-level loss that has been successfully applied to train recurrent neural network (RNN) models for automatic speech recognition. However, one major weakness of CTC is the conditional independence assumption that makes it difficult for the model to learn label dependencies. In this paper, we propose stimulated CTC, which uses stimulated learning to help CTC models learn label dependencies implicitly by using an auxiliary RNN to generate the appropriate stimuli. This stimuli comes in the form of an additional stimulation loss term which encourages the model to learn said label dependencies. The auxiliary network is only used during training and the inference model has the same structure as a standard CTC model. The proposed stimulated CTC model achieves about 35% relative character error rate improvements on a synthetic gesture keyboard recognition task and over 30% relative word error rate improvements on the Librispeech automatic speech recognition tasks over a baseline model trained with CTC only.}},
  author       = {{Heymann, Jahn and Khe Chai Sim, Bo Li}},
  booktitle    = {{ICASSP 2019, Brighton, UK}},
  title        = {{{Improving CTC Using Stimulated Learning for Sequence Modeling}}},
  year         = {{2019}},
}

@inproceedings{15816,
  abstract     = {{Despite the strong modeling power of neural network acoustic models, speech enhancement has been shown to deliver additional word error rate improvements if multi-channel data is available. However, there has been a longstanding debate whether enhancement should also be carried out on the ASR training data. In an extensive experimental evaluation on the acoustically very challenging CHiME-5 dinner party data we show that: (i) cleaning up the training data can lead to substantial error rate reductions, and (ii) enhancement in training is advisable as long as enhancement in test is at least as strong as in training. This approach stands in contrast and delivers larger gains than the common strategy reported in the literature to augment the training database with additional artificially degraded speech. Together with an acoustic model topology consisting of initial CNN layers followed by factorized TDNN layers we achieve with 41.6% and 43.2% WER on the DEV and EVAL test sets, respectively, a new single-system state-of-the-art result on the CHiME-5 data. This is a 8% relative improvement compared to the best word error rate published so far for a speech recognizer without system combination.}},
  author       = {{Zorila, Catalin and Boeddeker, Christoph and Doddipatla, Rama and Haeb-Umbach, Reinhold}},
  booktitle    = {{ASRU 2019, Sentosa, Singapore}},
  title        = {{{An Investigation Into the Effectiveness of Enhancement in ASR Training and Test for Chime-5 Dinner Party Transcription}}},
  year         = {{2019}},
}

@inproceedings{14822,
  abstract     = {{Multi-talker speech and moving speakers still pose a significant challenge to automatic speech recognition systems. Assuming an enrollment utterance of the target speakeris available, the so-called SpeakerBeam concept has been recently proposed to extract the target speaker from a speech mixture. If multi-channel input is available, spatial properties of the speaker can be exploited to support the source extraction. In this contribution we investigate different approaches to exploit such spatial information. In particular, we are interested in the question, how useful this information is if the target speaker changes his/her position. To this end, we present a SpeakerBeam-based source extraction network that is adapted to work on moving speakers by recursively updating the beamformer coefficients. Experimental results are presented on two data sets, one with articially created room impulse responses, and one with real room impulse responses and noise recorded in a conference room. Interestingly, spatial features turn out to be advantageous even if the speaker position changes.}},
  author       = {{Heitkaemper, Jens and Feher, Thomas and Freitag, Michael and Haeb-Umbach, Reinhold}},
  booktitle    = {{International Conference on Statistical Language and Speech Processing 2019, Ljubljana, Slovenia}},
  title        = {{{A Study on Online Source Extraction in the Presence of Changing Speaker Positions}}},
  year         = {{2019}},
}

@inproceedings{14824,
  abstract     = {{This paper deals with multi-channel speech recognition in scenarios with multiple speakers. Recently, the spectral characteristics of a target speaker, extracted from an adaptation utterance, have been used to guide a neural network mask estimator to focus on that speaker. In this work we present two variants of speakeraware neural networks, which exploit both spectral and spatial information to allow better discrimination between target and interfering speakers. Thus, we introduce either a spatial preprocessing prior to the mask estimation or a spatial plus spectral speaker characterization block whose output is directly fed into the neural mask estimator. The target speaker’s spectral and spatial signature is extracted from an adaptation utterance recorded at the beginning of a session. We further adapt the architecture for low-latency processing by means of block-online beamforming that recursively updates the signal statistics. Experimental results show that the additional spatial information clearly improves source extraction, in particular in the same-gender case, and that our proposal achieves state-of-the-art performance in terms of distortion reduction and recognition accuracy.}},
  author       = {{Martin-Donas, Juan M. and Heitkaemper, Jens and Haeb-Umbach, Reinhold and Gomez, Angel M. and Peinado, Antonio M.}},
  booktitle    = {{INTERSPEECH 2019, Graz, Austria}},
  title        = {{{Multi-Channel Block-Online Source Extraction based on Utterance Adaptation}}},
  year         = {{2019}},
}

@inproceedings{14826,
  abstract     = {{In this paper, we present Hitachi and Paderborn University’s joint effort for automatic speech recognition (ASR) in a dinner party scenario. The main challenges of ASR systems for dinner party recordings obtained by multiple microphone arrays are (1) heavy speech overlaps, (2) severe noise and reverberation, (3) very natural onversational content, and possibly (4) insufficient training data. As an example of a dinner party scenario, we have chosen the data presented during the CHiME-5 speech recognition challenge, where the baseline ASR had a 73.3% word error rate (WER), and even the best performing system at the CHiME-5 challenge had a 46.1% WER. We extensively investigated a combination of the guided source separation-based speech enhancement technique and an already proposed strong ASR backend and found that a tight combination of these techniques provided substantial accuracy improvements. Our final system achieved WERs of 39.94% and 41.64% for the development and evaluation data, respectively, both of which are the best published results for the dataset. We also investigated with additional training data on the official small data in the CHiME-5 corpus to assess the intrinsic difficulty of this ASR task.}},
  author       = {{Kanda, Naoyuki and Boeddeker, Christoph and Heitkaemper, Jens and Fujita, Yusuke and Horiguchi, Shota and Haeb-Umbach, Reinhold}},
  booktitle    = {{INTERSPEECH 2019, Graz, Austria}},
  title        = {{{Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR}}},
  year         = {{2019}},
}

@article{14990,
  abstract     = {{We investigate optical microresonators consisting of either one or two coupled rectangular strips between upper and lower slab waveguides. The cavities are evanescently excited under oblique angles by thin-film guided, in-plane unguided waves supported by one of the slab waveguides. Beyond a specific incidence angle, losses are fully suppressed. The interaction between the guided mode of the cavity-strip and the incoming slab modes leads to resonant behavior for specific incidence angles and gaps. For a single cavity, at resonance, the input power is equally split among each of the four output ports, while for two cavities an add-drop filter can be realized that, at resonance, routes the incoming power completely to the forward drop waveguide via the cavity. For both applications, the strength of the interaction is controlled by the gaps between cavities and waveguides.}},
  author       = {{Ebers, Lena and Hammer, Manfred and Berkemeier, Manuel B. and Menzel, Alexander and Förstner, Jens}},
  issn         = {{2578-7519}},
  journal      = {{OSA Continuum}},
  keywords     = {{tet_topic_waveguides}},
  pages        = {{3288}},
  title        = {{{Coupled microstrip-cavities under oblique incidence of semi-guided waves: a lossless integrated optical add-drop filter}}},
  doi          = {{10.1364/osac.2.003288}},
  volume       = {{2}},
  year         = {{2019}},
}

@inproceedings{15164,
  author       = {{Feldmann, Nadine and Jurgelucks, Benjamin and Claes, Leander and Henning, Bernd}},
  booktitle    = {{2019 International Congress on Ultrasonics}},
  title        = {{{A sensitivity-based optimisation procedure for the characterisation of piezoelectric discs}}},
  doi          = {{10.1121/2.0001070}},
  year         = {{2019}},
}

@inproceedings{15247,
  author       = {{Grabo, Matti and Weber, Daniel and Paul, Andreas and Klaus, Tobias and Bermpohl, Wolfgang and Krauter, Stefan and Kenig, Eugeny}},
  location     = {{Nordhausen}},
  title        = {{{Entwicklung eines thermischen 1D-Simulationsmodells zur Bestimmung der Temperaturverteilung in Solarmodulen}}},
  year         = {{2019}},
}

@inproceedings{15248,
  author       = {{Grabo, Matti and Weber, Daniel and Paul, Andreas and Klaus, Tobias and Bermpohl, Wolfgang and Kenig, Eugeny}},
  location     = {{Frankfurt am Main}},
  title        = {{{Numerische Untersuchung der Temperaturverteilung in PCM-integrierten Solarmodulen}}},
  year         = {{2019}},
}

@inproceedings{15261,
  author       = {{Lugovtsova, Yevgeniya and Johannesmann, Sarah and Henning, Bernd and Prager, Jens}},
  booktitle    = {{2019 International Congress on Ultrasonics}},
  location     = {{Bruges}},
  publisher    = {{Acoustical Society of America}},
  title        = {{{Analysis of Lamb wave mode repulsion and its implications to the characterisation of adhesive bonding strength}}},
  doi          = {{10.1121/2.0001074}},
  year         = {{2019}},
}

@inproceedings{16076,
  author       = {{Hetkämper, Tim and Claes, Leander and Henning, Bernd}},
  booktitle    = {{2019 International Congress on Ultrasonics}},
  location     = {{Bruges}},
  title        = {{{Evolutionary algorithm for the design of passive electric matching networks for ultrasonic transducers}}},
  doi          = {{10.1121/2.0001110}},
  year         = {{2019}},
}

@article{13048,
  abstract     = {{Marginal hardware introduces severe reliability threats throughout the life cycle of a system. Although marginalities may not affect the functionality of a circuit immediately after manufacturing, they can degrade into hard failures and must be screened out during manufacturing test to prevent early life failures. Furthermore, their evolution in the field must be proactively monitored by periodic tests before actual failures occur. In recent years small delay faults have gained increasing attention as possible indicators of marginal hardware. However, small delay faults on short paths may be undetectable even with advanced timing aware ATPG. Faster-than-at-speed test (FAST) can detect such hidden delay faults, but so far FAST has mainly been restricted to manufacturing test.}},
  author       = {{Kampmann, Matthias and A. Kochte, Michael and Liu, Chang and Schneider, Eric and Hellebrand, Sybille and Wunderlich, Hans-Joachim}},
  issn         = {{1937-4151}},
  journal      = {{IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD)}},
  number       = {{10}},
  pages        = {{1956 -- 1968}},
  publisher    = {{IEEE}},
  title        = {{{Built-in Test for Hidden Delay Faults}}},
  volume       = {{38}},
  year         = {{2019}},
}

@article{13143,
  author       = {{Claes, Leander and Hülskämper, Lars Moritz and Baumhögger, Elmar and Feldmann, Nadine and Chatwell, René Spencer and Vrabec, Jadran and Henning, Bernd}},
  issn         = {{2196-7113}},
  journal      = {{tm - Technisches Messen}},
  pages        = {{2--6}},
  title        = {{{Acoustic absorption measurement for the determination of the volume viscosity of pure fluids / Messverfahren für die akustischen Absorption zur Bestimmung der Volumenviskosität reiner Fluide}}},
  doi          = {{10.1515/teme-2019-0038}},
  year         = {{2019}},
}

@inproceedings{13271,
  abstract     = {{Automatic meeting analysis comprises the tasks of speaker counting, speaker diarization, and the separation of overlapped speech, followed by automatic speech recognition. This all has to be carried out on arbitrarily long sessions and, ideally, in an online or block-online manner. While significant progress has been made on individual tasks, this paper presents for the first time an all-neural approach to simultaneous speaker counting, diarization and source separation. The NN-based estimator operates in a block-online fashion and tracks speakers even if they remain silent for a number of time blocks, thus learning a stable output order for the separated sources. The neural network is recurrent over time as well as over the number of sources. The simulation experiments show that state of the art separation performance is achieved, while at the same time delivering good diarization and source counting results. It even generalizes well to an unseen large number of blocks.}},
  author       = {{von Neumann, Thilo and Kinoshita, Keisuke and Delcroix, Marc and Araki, Shoko and Nakatani, Tomohiro and Haeb-Umbach, Reinhold}},
  booktitle    = {{ICASSP 2019, Brighton, UK}},
  title        = {{{All-neural Online Source Separation, Counting, and Diarization for Meeting Analysis}}},
  year         = {{2019}},
}

@inproceedings{10042,
  author       = {{Johannesmann, Sarah and Springer, Dimitri and Thiel, Christian and Henning, Bernd}},
  booktitle    = {{Fortschritte der Akustik - DAGA 2019}},
  editor       = {{Gesellschaft für Akustik e.V., Deutsche}},
  location     = {{Rostock}},
  pages        = {{1055--1058}},
  publisher    = {{Deutsche Gesellschaft für Akustik}},
  title        = {{{Störeffektunterdrückung in 2D-Messdaten mittels DiscoGAN}}},
  volume       = {{45}},
  year         = {{2019}},
}

@inproceedings{10135,
  author       = {{Webersen, Manuel and Hüttner, Matthias and Woitschek, Fabian and Moritzer, Elmar and Henning, Bernd}},
  booktitle    = {{Fortschritte der Akustik - DAGA 2019}},
  location     = {{Rostock}},
  title        = {{{Akustische Charakterisierung der mechanischen Eigenschaften künstlich gealterter Polymere}}},
  year         = {{2019}},
}

@inproceedings{13647,
  author       = {{Claes, Leander and Johannesmann, Sarah and Baumhögger, Elmar and Henning, Bernd}},
  booktitle    = {{2019 International Congress on Ultrasonics}},
  location     = {{Bruges}},
  title        = {{{Quantification of frequency-dependent absorption phenomena}}},
  doi          = {{10.1121/2.0001043}},
  year         = {{2019}},
}

@article{25030,
  author       = {{Schenke, Maximilian and Kirchgässner, Wilhelm and Wallscheid, Oliver}},
  issn         = {{1551-3203}},
  journal      = {{IEEE Transactions on Industrial Informatics}},
  pages        = {{4650--4658}},
  title        = {{{Controller Design for Electrical Drives by Deep Reinforcement Learning: A Proof of Concept}}},
  doi          = {{10.1109/tii.2019.2948387}},
  year         = {{2019}},
}

@inproceedings{29885,
  author       = {{Joy, Meryl Teresa and Böcker, Joachim}},
  booktitle    = {{2018 IEEE International Conference on Power Electronics, Drives and Energy Systems (PEDES)}},
  location     = {{Chennai, India}},
  publisher    = {{IEEE}},
  title        = {{{Speed Estimation in Induction Machines at all Speed Ranges Using Sensing Windings}}},
  doi          = {{10.1109/pedes.2018.8707494}},
  year         = {{2019}},
}