@article{15416, author = {{Jochen Baumeister}}, journal = {{Quick And Easy Journal Title}}, title = {{{New Quick And Easy Publication - Will be edited by LibreCat team}}}, 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{15908, author = {{Müller, Jens and Brinkmann, Marcus and Poddebniak, Damian and Böck, Hanno and Schinzel, Sebastian and Somorovsky, Juraj and Schwenk, Jörg}}, booktitle = {{28th {USENIX} Security Symposium ({USENIX} Security 19)}}, isbn = {{978-1-939133-06-9}}, pages = {{1011--1028}}, publisher = {{{USENIX} Association}}, title = {{{"Johnny, you are fired!" -- Spoofing OpenPGP and S/MIME Signatures in Emails}}}, year = {{2019}}, } @inproceedings{15909, author = {{Merget, Robert and Somorovsky, Juraj and Aviram, Nimrod and Young, Craig and Fliegenschmidt, Janis and Schwenk, Jörg and Shavitt, Yuval}}, booktitle = {{28th {USENIX} Security Symposium ({USENIX} Security 19)}}, isbn = {{978-1-939133-06-9}}, pages = {{1029--1046}}, publisher = {{{USENIX} Association}}, title = {{{Scalable Scanning and Automatic Classification of TLS Padding Oracle Vulnerabilities}}}, year = {{2019}}, } @inproceedings{14568, author = {{Heindorf, Stefan and Scholten, Yan and Engels, Gregor and Potthast, Martin}}, booktitle = {{INFORMATIK}}, pages = {{289--290}}, title = {{{Debiasing Vandalism Detection Models at Wikidata (Extended Abstract)}}}, doi = {{10.18420/inf2019_48}}, 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}}, } @techreport{14902, author = {{Mair, Christina and Scheffler, Wolfram and Senger, Isabell and Sureth-Sloane, Caren}}, title = {{{Analyse der Veränderung der zwischenstaatlichen Gewinnaufteilung bei Einführung einer standardisierten Gewinnverteilungsmethode am Beispiel des Einsatzes von 3D-Druckern}}}, volume = {{42}}, 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}}, } @article{15002, abstract = {{Many problem settings in machine learning are concerned with the simultaneous prediction of multiple target variables of diverse type. Amongst others, such problem settings arise in multivariate regression, multi-label classification, multi-task learning, dyadic prediction, zero-shot learning, network inference, and matrix completion. These subfields of machine learning are typically studied in isolation, without highlighting or exploring important relationships. In this paper, we present a unifying view on what we call multi-target prediction (MTP) problems and methods. First, we formally discuss commonalities and differences between existing MTP problems. To this end, we introduce a general framework that covers the above subfields as special cases. As a second contribution, we provide a structured overview of MTP methods. This is accomplished by identifying a number of key properties, which distinguish such methods and determine their suitability for different types of problems. Finally, we also discuss a few challenges for future research.}}, author = {{Waegeman, Willem and Dembczynski, Krzysztof and Hüllermeier, Eyke}}, issn = {{1573-756X}}, journal = {{Data Mining and Knowledge Discovery}}, number = {{2}}, pages = {{293--324}}, title = {{{Multi-target prediction: a unifying view on problems and methods}}}, doi = {{10.1007/s10618-018-0595-5}}, volume = {{33}}, year = {{2019}}, } @inproceedings{15007, author = {{Melnikov, Vitaly and Hüllermeier, Eyke}}, booktitle = {{Proceedings ACML, Asian Conference on Machine Learning (Proceedings of Machine Learning Research, 101)}}, title = {{{Learning to Aggregate: Tackling the Aggregation/Disaggregation Problem for OWA}}}, doi = {{10.1016/j.jmva.2019.02.017}}, year = {{2019}}, } @inproceedings{15011, author = {{Tornede, Alexander and Wever, Marcel Dominik and Hüllermeier, Eyke}}, booktitle = {{Proceedings - 29. Workshop Computational Intelligence, Dortmund, 28. - 29. November 2019}}, editor = {{Hoffmann, Frank and Hüllermeier, Eyke and Mikut, Ralf}}, isbn = {{978-3-7315-0979-0}}, location = {{Dortmund}}, pages = {{135--146}}, publisher = {{KIT Scientific Publishing, Karlsruhe}}, title = {{{Algorithm Selection as Recommendation: From Collaborative Filtering to Dyad Ranking}}}, year = {{2019}}, } @article{16337, author = {{Brandt, Sascha and Jähn, Claudius and Fischer, Matthias and Meyer auf der Heide, Friedhelm}}, issn = {{0167-7055}}, journal = {{Computer Graphics Forum}}, location = {{Seoul, South Korea}}, number = {{7}}, pages = {{413--424}}, title = {{{Visibility‐Aware Progressive Farthest Point Sampling on the GPU}}}, doi = {{10.1111/cgf.13848}}, volume = {{38}}, year = {{2019}}, } @unpublished{16341, abstract = {{We present a technique for rendering highly complex 3D scenes in real-time by generating uniformly distributed points on the scene's visible surfaces. The technique is applicable to a wide range of scene types, like scenes directly based on complex and detailed CAD data consisting of billions of polygons (in contrast to scenes handcrafted solely for visualization). This allows to visualize such scenes smoothly even in VR on a HMD with good image quality, while maintaining the necessary frame-rates. In contrast to other point based rendering methods, we place points in an approximated blue noise distribution only on visible surfaces and store them in a highly GPU efficient data structure, allowing to progressively refine the number of rendered points to maximize the image quality for a given target frame rate. Our evaluation shows that scenes consisting of a high amount of polygons can be rendered with interactive frame rates with good visual quality on standard hardware.}}, author = {{Brandt, Sascha and Jähn, Claudius and Fischer, Matthias and Meyer auf der Heide, Friedhelm}}, booktitle = {{arXiv:1904.08225}}, title = {{{Rendering of Complex Heterogenous Scenes using Progressive Blue Surfels}}}, year = {{2019}}, } @misc{13128, author = {{Bröcher, Henrik}}, publisher = {{Universität Paderborn}}, title = {{{Rational Secure Multiparty Computation}}}, year = {{2019}}, } @inproceedings{13138, abstract = {{Mobile app stores like Apple's AppStore or Google's PlayStore are highly competitive markets for third-party developers wanting to develop successful applications. During the development process, many developers focus on the multitude of product functions but neglect the business model as an equally important part. As a result, developers often fail to meet customer needs, leading to unnecessary development costs and poor market penetration. This, in turn, raises the question of how we intertwine the business model and product functions during the development process to ensure a better alignment between the two. In this paper, we show this intertwined development by adapting the concept of Twin Peaks to the business model and product functions. Based on feature modeling as an abstraction layer, we introduce the concept of a Business Model Decision Line (BMDL) to structure the business model decisions and their relation to product functions structured in a Software Product Line (SPL). The basis of our feature models is the analysis of top listed applications in the app stores of Apple and Google. To create and modify both models, we provide an incremental feature structuring and iterative feature selection process. This combination of abstraction layer and development process supports third-party developers to build successful applications both from a business and a product perspective. }}, author = {{Gottschalk, Sebastian and Rittmeier, Florian and Engels, Gregor}}, booktitle = {{Software Business}}, editor = {{Hyrynsalmi, Sami and Suoranta, Mari and Nguyen-Duc, Anh and Tyrväinen, Pasi and Abrahamsson, Pekka}}, keywords = {{Intertwined Development, Twin Peaks, Feature Model, Business Model, Product Functions}}, location = {{ Jyväskylä}}, number = {{1}}, pages = {{192--207}}, publisher = {{Springer International Publishing}}, title = {{{Intertwined Development of Business Model and Product Functions for Mobile Applications: A Twin Peak Feature Modeling Approach}}}, doi = {{10.1007/978-3-030-33742-1_16}}, volume = {{370}}, year = {{2019}}, } @book{13139, editor = {{Rezat, Sebastian and Fan, Lianghuo and Hattermann, Mathias and Schumacher, Jan and Wuschke, Holger}}, location = {{Paderborn}}, pages = {{392}}, publisher = {{Universitätsbibliothek Paderborn}}, title = {{{Proceedings of the Third International Conference on Mathematics Textbook Research and Development: 16-19 September 2019 Paderborn, Germany}}}, doi = {{10.17619/UNIPB/1-768}}, 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}}, }