@inproceedings{TwiefelBaumannHeinrichetal., author = {Twiefel, Johannes and Baumann, Timo and Heinrich, Stefan and Wermter, Stefan}, title = {Improving Domain-independent Cloud-based Speech Recognition with Domain-dependent Phonetic Post-processing}, series = {AAAI 2014 - Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI-14), Qu{\´e}bec, CA, July 27-31, 2014}, booktitle = {AAAI 2014 - Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI-14), Qu{\´e}bec, CA, July 27-31, 2014}, publisher = {Association for the Advancement of Artificial Intelligence}, doi = {10.1609/aaai.v28i1.8929}, pages = {1529 -- 1535}, abstract = {Automatic speech recognition (ASR) technology has been developed to such a level that off-the-shelf distributed speech recognition services are available (free of cost), which allow researchers to integrate speech into their applications with little development effort or expert knowledge leading to better results compared with previously used open-source tools. Often, however, such services do not accept language models or grammars but process free speech from any domain. While results are very good given the enormous size of the search space, results frequently contain out-of-domain words or constructs that cannot be understood by subsequent domain-dependent natural language understanding (NLU) components. We present a versatile post-processing technique based on phonetic distance that integrates domain knowledge with open-domain ASR results, leading to improved ASR performance. Notably, our technique is able to make use of domain restrictions using various degrees of domain knowledge, ranging from pure vocabulary restrictions via grammars or N-Grams to restrictions of the acceptable utterances. We present results for a variety of corpora (mainly from human-robot interaction) where our combined approach significantly outperforms Google ASR as well as a plain open-source ASR solution.}, language = {en} } @inproceedings{KenningtonKousidisBaumannetal., author = {Kennington, Casey and Kousidis, Spyros and Baumann, Timo and Buschmeier, Hendrik and Kopp, Stefan and Schlangen, David}, title = {Better Driving and Recall When In-car Information Presentation Uses Situationally-Aware Incremental Speech Output Generation}, series = {Proceedings of the 6th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, AutomotiveUI '14, Seattle WA, USA, September 17 - 19, 2014}, booktitle = {Proceedings of the 6th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, AutomotiveUI '14, Seattle WA, USA, September 17 - 19, 2014}, editor = {Miller, Erika and Wu, Yuqing}, publisher = {ACM}, address = {New York, NY}, doi = {10.1145/2667317.2667332}, pages = {1 -- 7}, abstract = {It is established that driver distraction is the result of sharing cognitive resources between the primary task (driving) and any other secondary task. In the case of holding conversations, a human passenger who is aware of the driving conditions can choose to interrupt his speech in situations potentially requiring more attention from the driver, but in-car information systems typically do not exhibit such sensitivity. We have designed and tested such a system in a driving simulation environment. Unlike other systems, our system delivers information via speech (calendar entries with scheduled meetings) but is able to react to signals from the environment to interrupt when the driver needs to be fully attentive to the driving task and subsequently resume its delivery. Distraction is measured by a secondary short-term memory task. In both tasks, drivers perform significantly worse when the system does not adapt its speech, while they perform equally well to control conditions (no concurrent task) when the system intelligently interrupts and resumes.}, language = {en} } @inproceedings{Baumann, author = {Baumann, Timo}, title = {Partial Representations Improve the Prosody of Incremental Speech Synthesis}, series = {Interspeech 2014, Singapore, 14-18 September 2014}, booktitle = {Interspeech 2014, Singapore, 14-18 September 2014}, doi = {10.21437/Interspeech.2014-199}, pages = {2932 -- 2936}, abstract = {When humans speak, they do not plan their full utterance inall detail before beginning to speak, nor do they speak piece-by-piece and ignoring their full message - instead humans usepartial representations in which they fill in the missing partsas the utterance unfolds. Incremental speech synthesizers, incontrast, have not yet made use of partial representations and theinformation contained there-in.We analyze the quality of prosodic parameter assignments(pitch and duration) generated from partial utterance specifi-cations (substituting defaults for missing features) in order todetermine the requirements that symbolic incremental prosodymodelling should meet. We find that broader, higher-level infor-mation helps to improve prosody even if lower-level informationabout the near future is yet unavailable. Furthermore, we findthat symbolic phrase-level or utterance-level information is mosthelpful towards the end of the phrase or utterance, respectively,that is, when this information is becoming available even in theincremental case. Thus, the negative impact of incremental pro-cessing can be minimized by using partial representations thatare filled in incrementally.}, language = {en} } @inproceedings{KousidisKenningtonBaumannetal., author = {Kousidis, Spyros and Kennington, Casey and Baumann, Timo and Buschmeier, Hendrik and Kopp, Stefan and Schlangen, David}, title = {A Multimodal In-Car Dialogue System That Tracks The Driver's Attention}, series = {Proceedings of the 16th International Conference on Multimodal Interaction, ICMI '14, November 12 - 16 2014, Istanbul}, booktitle = {Proceedings of the 16th International Conference on Multimodal Interaction, ICMI '14, November 12 - 16 2014, Istanbul}, editor = {Ali Salah, Albert}, publisher = {ACM}, address = {New York, NY}, isbn = {9781450328852}, doi = {10.1145/2663204.2663244}, pages = {26 -- 33}, abstract = {When a passenger speaks to a driver, he or she is co-located with the driver, is generally aware of the situation, and can stop speaking to allow the driver to focus on the driving task. In-car dialogue systems ignore these important aspects, making them more distracting than even cell-phone conversations. We developed and tested a "situationally-aware" dialogue system that can interrupt its speech when a situation which requires more attention from the driver is detected, and can resume when driving conditions return to normal. Furthermore, our system allows driver-controlled resumption of interrupted speech via verbal or visual cues (head nods). Over two experiments, we found that the situationally-aware spoken dialogue system improves driving performance and attention to the speech content, while driver-controlled speech resumption does not hinder performance in either of these two tasks}, language = {en} } @inproceedings{BaumannLindner, author = {Baumann, Timo and Lindner, Felix}, title = {Incremental Speech Production for Polite and Natural Personal-Space Intrusion}, series = {Social robotics : 7th International Conference, ICSR 2015, Paris, France, October 26-30, 2015, Proceedings}, booktitle = {Social robotics : 7th International Conference, ICSR 2015, Paris, France, October 26-30, 2015, Proceedings}, editor = {Tapus, Adriana and Andr{\´e}, Elisabeth and Martin, Jean-Claude}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-25553-8}, doi = {10.1007/978-3-319-25554-5_8}, pages = {72 -- 82}, abstract = {We propose to use a model of personal space to initiate communication while passing a human thereby acknowledging that humans are not just a special kind of obstacle to be avoided but potential interaction partners. As a simple form of interaction, our system communicates an apology while closely passing a human. To this end, we present a software architecture that integrates a social-spaces knowledge base and a component for incremental speech production. Incrementality ensures that the robot's utterance can be adapted to fit the developing situation in a natural way. Observer ratings show that personal-space intrusion is perceived as both natural and polite if the robot has the capability to utter and adapt an apology in an incremental way whereas it is perceived as unfriendly if the robot intrudes personal space without saying anything. Moreover, the robot is perceived as less natural if it does not adapt.}, language = {en} } @inproceedings{BaumannKenningtonHoughetal., author = {Baumann, Timo and Kennington, Casey and Hough, Julian and Schlangen, David}, title = {Recognising Conversational Speech: What an Incremental ASR Should Do for a Dialogue System and How to Get There}, series = {Proceedings of the International Workshop Series on Spoken Dialogue Systems Technology (IWSDS) 2016}, booktitle = {Proceedings of the International Workshop Series on Spoken Dialogue Systems Technology (IWSDS) 2016}, abstract = {Automatic speech recognition (ASR) is not only becoming increasingly accurate, but also increasingly adapted for producing timely, incremental output. However, overall accuracy and timeliness alone are insufficient when it comes to interactive dialogue systems which require stability in the output and responsivity to the utterance as it is unfolding. Furthermore, for a dialogue system to deal with phenomena such as disfluencies, to achieve deep understanding of user utterances these should be preserved or marked up for use by downstream components, such as language understanding, rather than be filtered out. Similarly, word timing can be informative for analyzing deictic expressions in a situated environment and should be available for analysis. Here we investigate the overall accuracy and incremental performance of three widely used systems and discuss their suitability for the aforementioned perspectives. From the differing performance along these measures we provide a picture of the requirements for incremental ASR in dialogue systems and describe freely available tools for using and evaluating incremental ASR.}, language = {en} } @inproceedings{BaumannLindner, author = {Baumann, Timo and Lindner, Felix}, title = {Towards a Social Robot that Incrementally Justifies Personal-Space Intrusion}, series = {Proceedings of the Workshop Towards a Framework for Joint Action 2015}, booktitle = {Proceedings of the Workshop Towards a Framework for Joint Action 2015}, abstract = {Robots should appropriately give reasons for their actions when these actions affect a human's action or goal space. Communicating reasons may help the human understand the robot's intents and may initiate joint action, i. e., accepting the robot's goals and cooperating on the robot's actions. However, to be efficient, the communication of reasons should be limited to the necessary rather than to completeness, conforming to the Gricean Maxim of Quantity. Furthermore, what is necessary only becomes apparent as the situation evolves and hence, for seamless interaction, ongoing utterances must be adapted as they happen. We present a system that flexibly gives reasons in a reduced setting in which the robot needs to intrude a human's personal space in order to reach its goal.}, language = {en} } @inproceedings{PougetHueberBaillyetal., author = {Pouget, Ma{\"e}l and Hueber, Thomas and Bailly, G{\´e}rard and Baumann, Timo}, title = {HMM training strategy for incremental speech synthesis}, series = {Interspeech 2015, Dresden, Germany, 6-10 September 2015}, booktitle = {Interspeech 2015, Dresden, Germany, 6-10 September 2015}, publisher = {ISCA}, doi = {10.21437/Interspeech.2015-304}, pages = {1201 -- 1205}, abstract = {Incremental speech synthesis aims at delivering the synthetic voice while the sentence is still being typed. One of the main challenges is the online estimation of the target prosody from a partial knowledge of the sentence's syntactic structure. In the context of HMM-based speech synthesis, this typically results in missing segmental and suprasegmental features, which describe the linguistic context of each phoneme. This study describes a voice training procedure which integrates explicitly a potential uncertainty on some contextual features. The proposed technique is compared to a baseline approach (previously published), which consists in substituting a missing contextual feature by a default value calculated on the training set. Both techniques were implemented in a HMM-based Text-To-Speech system for French, and compared using objective and perceptual measurements. Experimental results show that the proposed strategy outperforms the baseline technique for this language.}, language = {en} } @inproceedings{Baumann, author = {Baumann, Timo}, title = {Decision Tree Usage for Incremental Parametric Speech Synthesis}, series = {Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2014, 4-9 May 2014, Florence, Italy}, booktitle = {Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2014, 4-9 May 2014, Florence, Italy}, publisher = {IEEE}, doi = {10.1109/ICASSP.2014.6854316}, pages = {3847 -- 3851}, abstract = {Human speakers plan and deliver their utterances incrementally, piece-by-piece, and it is obvious that their choice regarding phonetic details (and the details' peculiarities) is rarely determined by globally optimal solutions. In contrast, parametric speech synthesizers use a full-utterance context when optimizing vocoding parameters and when determing HMM states. Apart from being cognitively implausible, this impedes incremental use-cases, where the future context is often at least partially unavailable. This paper investigates the `locality' of features in parametric speech synthesis voices and takes some missing steps towards better HMM state selection and prosody modelling for incremental speech synthesis.}, language = {en} } @inproceedings{BaumannBangaloreHirschberg, author = {Baumann, Timo and Bangalore, Srinivas and Hirschberg, Julia}, title = {Towards Simultaneous Interpreting: The Timing of Incremental Machine Translation and Speech Synthesis}, series = {Proceedings of the 11th International Workshop on Spoken Language Translation. Papers. Lake Tahoe, December 4th and 5th, 2014}, booktitle = {Proceedings of the 11th International Workshop on Spoken Language Translation. Papers. Lake Tahoe, December 4th and 5th, 2014}, editor = {Federico, Marcello and St{\"u}ker, Sebastian and Yvon, Fran{\c{c}}ois}, pages = {163 -- 168}, abstract = {In simultaneous interpreting, human experts incrementally construct and extend partial hypotheses about the source speaker's message, and start to verbalize a corresponding message in the target language, based on a partial translation - which may have to be corrected occasionally. They commence the target utterance in the hope that they will be able to finish understanding the source speaker's message and determine its translation in time for the unfolding delivery. Of course, both incremental understanding and translation by humans can be garden-pathed, although experts are able to optimize their delivery so as to balance the goals of minimal latency, translation quality and high speech fluency with few corrections. We investigate the temporal properties of both translation input and output to evaluate the tradeoff between low latency and translation quality. In addition, we estimate the improvements that can be gained with a tempo-elastic speech synthesizer.}, language = {en} } @article{MeyerSickendiekHusseinBaumann, author = {Meyer-Sickendiek, Burkhard and Hussein, Hussein and Baumann, Timo}, title = {Towards the Creation of a Poetry Translation Mapping System}, series = {Archives of Data Science, Series A}, volume = {5}, journal = {Archives of Data Science, Series A}, number = {1}, publisher = {Towards the Creation of a Poetry Translation Mapping System}, issn = {2363-9881}, doi = {10.5445/KSP/1000087327/21}, pages = {1 -- 15}, abstract = {The translation of poetry is a complex, multifaceted challenge: the translated text should communicate the same meaning, similar metaphoric expressions, and also match the style and prosody of the original poem. Research on machine poetry translation is existing since 2010, but for four reasons it is still rather insufficient: 1. The few approaches existing completely lack any knowledge about current developments in both lyric theory and translation theory. 2. They are based on very small datasets. 3. They mostly ignored the neural learning approach that superseded the long-standing dominance of phrase-based approaches within machine translation. 4. They have no concept concerning the pragmatic function of their research and the resulting tools. Our paper describes how to improve the existing research and technology for poetry translations in exactly these four points. With regards to 1) we will describe the "Poetics of Translation". With regards to 2) we will introduce the Worlds largest corpus for poetry translations from lyrikline. With regards to 3) we will describe first steps towards a neural machine translation of poetry. With regards to 4) we will describe first steps towards the development of a poetry translation mapping system.}, language = {en} } @misc{WardBaumannKarkhedkaretal., author = {Ward, Nigel and Baumann, Timo and Karkhedkar, Shreyas and Novick, David}, title = {Dynamic control of voice codec data rate}, abstract = {A method, system, and computer-usable non-transitory storage device for dynamic voice codec adaptation are disclosed. The voice codec adapts in real time to devote more bits to audio quality when it is most needed, and fewer bits to less important parts of utterances are disclosed. Dialog knowledge is utilized for compression opportunities to adjust the bitrate moment-by-moment, based on the inferred value of each frame. Frame importance and appropriate transmission fidelity is predicted based on prosodic features and models of dialog dynamics. This technique provides the same communications quality with less spectrum needs, fewer antennas, and less battery drain.}, language = {en} } @article{BrosigStrahringerWestner, author = {Brosig, Christoph and Strahringer, Susanne and Westner, Markus}, title = {From selling machinery to hybrid offerings}, series = {International Journal of Information Systems and Project Management}, volume = {10}, journal = {International Journal of Information Systems and Project Management}, number = {3}, publisher = {SciKA}, issn = {2182-7788}, doi = {10.12821/ijispm100301}, pages = {5 -- 27}, abstract = {The transition towards services has been imperative for manufacturing firms for years. The change from a productoriented to a more service-dominant business model affects the organizational structure of firms. However, literature provides limited insights into how manufacturing firms organize themselves in this transition. Even though digital technologies are critical for the transition, it is unclear how to orchestrate digital and traditional Information Technology (IT) resources in manufacturing firms accordingly. We analyze the case of a typical manufacturing firm that has adjusted its structure to reorganize for solution offerings based on product, service, and digital components. Our results describe a hybrid organizational structure that splits front- and back-end units. The back-end units are split along solution components. Digital IT resources are internalized and governed decentrally, with traditional IT resources being outsourced and steered centrally. Our findings contribute to digital servitization research by clarifying the overarching as well as the digital and traditional IT-related organization for manufacturing firms.}, language = {en} } @inproceedings{SchindlerSkornia, author = {Schindler, Timo and Skornia, Christoph}, title = {Secure Parallel Processing of Big Data Using Order-Preserving Encryption on Google BigQuery}, series = {INFORMATIK 2016, Jahrestagung der Gesellschaft f{\"u}r Informatik e.V., 2016 Proceedings}, volume = {259}, booktitle = {INFORMATIK 2016, Jahrestagung der Gesellschaft f{\"u}r Informatik e.V., 2016 Proceedings}, publisher = {Gesellschaft f{\"u}r Informatik}, address = {Bonn}, isbn = {978-3-88579-653-4}, doi = {10.48550/arXiv.1608.07981}, pages = {343 -- 352}, abstract = {With the increase of centralization of resources in IT-infrastructure and the growing amount of cloud services, database management systems (DBMS) will be more and more outsourced to Infrastructure-as-a-Service (IaaS) providers. The outsourcing of entire databases, or the computation power for processing Big Data to an external provider also means that the provider has full access to the information contained in the database. In this article we propose a feasible solution with Order-Preserving Encryption (OPE) and further, state of the art, encryption methods to sort and process Big Data on external resources without exposing the unencrypted data to the IaaS provider. We also introduce a proof-of-concept client for Google BigQuery as example IaaS Provider.}, language = {en} } @inproceedings{JohannssenBiemannRemusetal., author = {Johannßen, Dirk and Biemann, Chris and Remus, Steffen and Baumann, Timo and Scheffer, David}, title = {GermEval 2020 Task 1 on the Classification and Regression of Cognitive and Motivational style from Text}, series = {Proceedings of the 5th SwissText \& 16th KONVENS Joint Conference 2020}, booktitle = {Proceedings of the 5th SwissText \& 16th KONVENS Joint Conference 2020}, address = {Zurich, Switzerland}, pages = {1 -- 10}, abstract = {This paper describes the tasks, databases, baseline systems, and summarizes submissions and results for the GermEval 2020 Shared Task 1 on the Classification and Regression of Cognitive and Motivational Style from Text. This shared task is divided into two subtasks, a regression task, and a classification task. Subtask 1 asks participants to reproduce a ranking of students based on average aptitude indicators such as different high school grades and different IQ scores. The second subtask aims to classify so-called implicit motives, which are projective testing procedures that can reveal unconscious desires. Besides five implicit motives, the target labels of Subtask 2 also contain one of six levels that describe the type of self-regulation when acting out a motive, which makes this task a multiclass-classification with 30 target labels. 3 participants submitted multiple systems. Subtask 1 was solved (best r = .3701) mainly with non-neural systems and statistical language representations, submissions for Subtask 2 utilized neural approaches and word embeddings (best macro F1 = 70.40). Not only were the tasks solvable, analyses by the participants even showed connections to the implicit psychometrics theory and behavioral observations made by psychologists. This paper describes the tasks, databases, baseline systems, and summarizes submissions and results for the GermEval 2020 Shared Task 1 on the Classification and Regression of Cognitive and Motivational Style from Text. This shared task is divided into two subtasks, a regression task, and a classification task. Subtask 1 asks participants to reproduce a ranking of students based on average aptitude indicators such as different high school grades and different IQ scores. The second subtask aims to classify so-called implicit motives, which are projective testing procedures that can reveal unconscious desires. Besides five implicit motives, the target labels of Subtask 2 also contain one of six levels that describe the type of self-regulation when acting out a motive, which makes this task a multiclass-classification with 30 target labels. 3 participants submitted multiple systems. Subtask 1 was solved (best r =.3701) mainly with non-neural systems and statistical language representations, submissions for Subtask 2 utilized neural approaches and word embeddings (best macro F1 = 70.40). Not only were the tasks solvable, analyses by the participants even showed connections to the implicit psychometrics theory and behavioral observations made by psychologists.}, language = {en} } @article{GegenfurtnerBoucheixGruberetal., author = {Gegenfurtner, Andreas and Boucheix, Jean-Michel and Gruber, Hans and Hauser, Florian and Lehtinen, Erno and Lowe, Richard K.}, title = {The gaze relational index as a measure of visual expertise}, series = {Journal of Expertise}, volume = {3}, journal = {Journal of Expertise}, number = {March}, publisher = {Michigan State University}, issn = {2573-2773}, pages = {32 -- 40}, abstract = {Eye tracking is a powerful technique that helps reveal how people process visual information. This paper discusses a novel metric for indicating expertise in visual information processing. Named the Gaze Relational Index (GRI), this metric is defined as the ratio of mean fixation duration to fixation count. Data from two eye-tracking studies of professional vision and visual expertise in using 3D dynamic medical visualizations are presented as cases to illustrate the suitability and additional benefits of the GRI. Calculated values of the GRI were higher for novices than for experts, and higher in non-representative, semi-familiar / unfamiliar task conditions than in domain-representative familiar tasks. These differences in GRI suggest that, compared to novices, experts engaged in more knowledge-driven, top-down processing that was characterized by quick, exploratory visual search. We discuss future research aiming to replicate the GRI in professional domains with complex visual stimuli and to identify the moderating role of cognitive ability on GRI estimates.}, language = {en} } @inproceedings{HusseinMeyerSickendiekBaumann, author = {Hussein, Hussein and Meyer-Sickendiek, Burkhard and Baumann, Timo}, title = {Free Verse and Beyond: How to Classify Post-modern Spoken Poetry}, series = {Proceedings of Speech Prosody: Tokyo, Japan, 25-28 May 2020}, booktitle = {Proceedings of Speech Prosody: Tokyo, Japan, 25-28 May 2020}, publisher = {ISCA}, doi = {10.21437/SpeechProsody.2020-141}, pages = {690 -- 694}, abstract = {This paper presents the classification of rhythmical patterns detected in post-modern spoken poetry by means of machine learning algorithms that use manually engineered features or automatically learnt representations. We used the world's largest corpus of spoken poetry from our partner lyrikline. We identified nine rhythmical patterns within a spectrum raging from a more fluent to a more disfluent poetic style. The text data analyzed by a statistical parser. Prosodic features of rhythmical patterns are identified by using the parser information. For the classification of rhythmical patterns, we used a neural networks-based approach which use text, audio, and pause information between poetic lines as features. Different combinations of features as well as the integration of feature engineering in the neural networks-based approach are tested. We compared the performance of both approaches (feature-based and neural network-based) using combinations of different features. The results show - by using the weighted average of f-measure for the evaluation - that the neural networks-based approach performed much better in classification of rhythmical patterns. The important improvement of the classification results lies in the use of the audio information. The integration of feature engineering in the neural networks-based approach yielded a very small result improvement.}, language = {en} } @inproceedings{BaumannMeyerSickendiek, author = {Baumann, Timo and Meyer-Sickendiek, Burkhard}, title = {Deep Learning meets Post-modern Poetry}, series = {TwinTalks 2020: Understanding and Facilitating Collaboration in Digital Humanities 2020, proceedings of the Twin Talks 2 and 3 workshops at DHN 2020 and DH 2020, Ottawa Canada and Riga Latvia, July 23 and October 20, 2020}, booktitle = {TwinTalks 2020: Understanding and Facilitating Collaboration in Digital Humanities 2020, proceedings of the Twin Talks 2 and 3 workshops at DHN 2020 and DH 2020, Ottawa Canada and Riga Latvia, July 23 and October 20, 2020}, editor = {Krauwer, Steven and Fišer, Darja}, publisher = {RWTH Aachen}, issn = {1613-0073}, pages = {30 -- 36}, abstract = {We summarize our project Rhythmicalizer in which we analyze a corpus of post-modern poetry in a combination of qualitative hermeneutical and computational methods, as we have run the project over the course of the past three years (and preparing it for some time before that). Interdisciplinary work is always challenging and we here focus on some of the highlights of our collaboration.}, language = {en} } @inproceedings{Baumann, author = {Baumann, Timo}, title = {How a Listener Influences the Speaker}, series = {Proceedings of Speech Prosody: Tokyo, Japan, 25-28 May 2020}, booktitle = {Proceedings of Speech Prosody: Tokyo, Japan, 25-28 May 2020}, publisher = {ISCA}, doi = {10.21437/SpeechProsody.2020-198}, pages = {970 -- 974}, abstract = {Listeners typically provide feedback while listening to a speaker in conversation and thereby engage in the co-construction of the interaction. We analyze the influence of the listener on the speaker by investigating how her verbal feedback signals help in modeling the speaker's language. We find that feedback from the listener may help in modeling the speaker's language, whether through the listener's feedback as transcribed, or the acoustic signal directly. We find the largest positive effects for end of sentence as well as for pauses mid-utterance, but also effects that indicate we successfully model elaborations of ongoing utterances that may result from the presence or absence of listener feedback.}, language = {en} } @article{BaumannKoehnHennig, author = {Baumann, Timo and K{\"o}hn, Arne and Hennig, Felix}, title = {The Spoken Wikipedia Corpus collection: Harvesting, alignment and an application to hyperlistening}, series = {Language Resources and Evaluation}, volume = {53}, journal = {Language Resources and Evaluation}, number = {2}, publisher = {Springer Nature}, doi = {10.1007/s10579-017-9410-y}, pages = {303 -- 329}, abstract = {Spoken corpora are important for speech research, but are expensive to create and do not necessarily reflect (read or spontaneous) speech 'in the wild'. We report on our conversion of the preexisting and freely available Spoken Wikipedia into a speech resource. The Spoken Wikipedia project unites volunteer readers of Wikipedia articles. There are initiatives to create and sustain Spoken Wikipedia versions in many languages and hence the available data grows over time. Thousands of spoken articles are available to users who prefer a spoken over the written version. We turn these semi-structured collections into structured and time-aligned corpora, keeping the exact correspondence with the original hypertext as well as all available metadata. Thus, we make the Spoken Wikipedia accessible for sustainable research. We present our open-source software pipeline that downloads, extracts, normalizes and text-speech aligns the Spoken Wikipedia. Additional language versions can be exploited by adapting configuration files or extending the software if necessary for language peculiarities. We also present and analyze the resulting corpora for German, English, and Dutch, which presently total 1005 h and grow at an estimated 87 h per year. The corpora, together with our software, are available via http://islrn.org/resources/684-927-624-257-3/. As a prototype usage of the time-aligned corpus, we describe an experiment about the preferred modalities for interacting with information-rich read-out hypertext. We find alignments to help improve user experience and factual information access by enabling targeted interaction.}, language = {en} } @inproceedings{SabooBaumann, author = {Saboo, Ashutosh and Baumann, Timo}, title = {Integration of Dubbing Constraints into Machine Translation}, series = {Proceedings of the Fourth Conference on Machine Translation, Volume 1: Research Papers}, booktitle = {Proceedings of the Fourth Conference on Machine Translation, Volume 1: Research Papers}, editor = {Bojar, Ondřej and Chatterjee, Rajen and Federmann, Christian and Fishel, Mark and Graham, Yvette and Haddow, Barry and Huck, Matthias and Yepes, Antonio Jimeno and Koehn, Philipp and Martins, Andr{\´e} and Monz, Christof and Negri, Matteo and N{\´e}v{\´e}ol, Aur{\´e}lie and Neves, Mariana and Post, Matt and Turchi, Marco and Verspoor, Karin}, publisher = {Association for Computational Linguistics}, address = {Stroudsburg, PA, USA}, doi = {10.18653/v1/W19-5210}, pages = {94 -- 101}, abstract = {Translation systems aim to perform a meaning-preserving conversion of linguistic material (typically text but also speech) from a source to a target language (and, to a lesser degree, the corresponding socio-cultural contexts). Dubbing, i.e., the lip-synchronous translation and revoicing of speech adds to this constraints about the close matching of phonetic and resulting visemic synchrony characteristics of source and target material. There is an inherent conflict between a translation's meaning preservation and 'dubbability' and the resulting trade-off can be controlled by weighing the synchrony constraints. We introduce our work, which to the best of our knowledge is the first of its kind, on integrating synchrony constraints into the machine translation paradigm. We present first results for the integration of synchrony constraints into encoder decoder-based neural machine translation and show that considerably more 'dubbable' translations can be achieved with only a small impact on BLEU score, and dubbability improves more steeply than BLEU degrades.}, language = {en} } @inproceedings{BrunthalerWaasKucera, author = {Brunthaler, Sebastian and Waas, Thomas and Kucera, Markus}, title = {On Verify and Validate a Next Generation Automotive Communication Network}, series = {Proceedings of the 9th International Conference on Pervasive and Embedded Computing and Communication Systems - PECCS, 121-127, 2019, Vienna, Austria}, booktitle = {Proceedings of the 9th International Conference on Pervasive and Embedded Computing and Communication Systems - PECCS, 121-127, 2019, Vienna, Austria}, publisher = {SCITEPRESS - Science and Technology Publications}, isbn = {978-989-758-385-8}, doi = {10.5220/0008191601210127}, pages = {121 -- 127}, abstract = {As a result of the enormous growth in data traffic for autonomous driving, the conventional in-vehicle network is no longer sufficient and requires new types of network concepts in a vehicle. This part of the automobile is known as the next generation communication network. Since the new car-systems can be extended by various services at any time, the network must adapt dynamically to new requirements wherever possible. For example, data flow must be configured dynamically between new services. Also data rates will be much higher in the future than today. This is one of the main reasons why we need to search for new technologies for data transfer in vehicles. This is based on an in-vehicle ethernet network. The process of configuring networks automatically has been discussed several times in recent years. One of the next steps is verifying and validating the automatic configuration process during the development of the new communication network. This research paper identifies several ways to ensure the automatically generated network configuration leads to a secure system. To achieve that, other parts of the company's enterprise IT architecture and network technologies, the conventional vehicle network and other options for verification and validation are analysed}, language = {en} } @inproceedings{HusseinMeyerSickendiekBaumann, author = {Hussein, Hussein and Meyer-Sickendiek, Burkhard and Baumann, Timo}, title = {Identification of Concrete Poetry within a Modern-Poetry Corpus using Neural Networks}, series = {Proceedings of the Quantitative Approaches to Versification Conference}, booktitle = {Proceedings of the Quantitative Approaches to Versification Conference}, address = {Prague, Czech Republic}, pages = {95 -- 104}, abstract = {This work aims to discern the poetics of concrete poetry by using a corpus-based classification focusing on the two most important techniques used within concrete poetry: semantic decomposition and syntactic permutation. We demonstrate how to identify concrete poetry in modern and postmodern free verse. A class contrasting to concrete poetry is defined on the basis of poems with complete and correct sentences. We used the data from lyrikline, which contain both the written as well as the spoken form of poems as read by the original author. We explored two approaches for the identification of concrete poetry. The first is based on the definition of concrete poetry in literary theory by the extraction of various types of features derived from a parser, such as verb, noun, comma, sentence ending, conjunction, and asemantic material. The second is a neural network-based approach, which is theoretically less informed by human insight, as it does not have access to features established by scholars. This approach used the following inputs: textual information and the spoken recitation of poetic lines as well as information about pauses between lines. The results based on the neural network are more accurate than the feature-based approach. The best results, calculated by the weighted F-measure, for the classification of concrete poetry vis-{\`a}-vis the contrasting class is 0.96}, language = {en} } @incollection{Baumann, author = {Baumann, Timo}, title = {Ranking and Comparing Speakers Based on Crowdsourced Pairwise Listener Ratings}, series = {Voice attractiveness: Studies on Sexy, Likable, and Charismatic Speakers}, booktitle = {Voice attractiveness: Studies on Sexy, Likable, and Charismatic Speakers}, editor = {Weiss, Benjamin and Trouvain, J{\"u}rgen and Barkat-Defradas, M{\´e}lissa and Ohala, John J.}, publisher = {Springer}, address = {Singapore}, isbn = {978-981-15-6626-4}, doi = {10.1007/978-981-15-6627-1_14}, pages = {263 -- 279}, abstract = {Speech quality and likability is a multi-faceted phenomenon consisting of a combination of perceptory features that cannot easily be computed nor weighed automatically. Yet, it is often easy to decide which of two voices one likes better, even though it would be hard to describe why, or to name the underlying basic perceptory features. Although likability is inherently subjective and individual preferences differ, generalizations are useful and there is often a broad intersubjective consensus about whether one speaker is more likeable than another. We present a methodology to efficiently create a likability ranking for many speakers from crowdsourced pairwise likability ratings which focuses manual rating effort on pairs of similar quality using an active sampling technique. Using this methodology, we collected pairwise likability ratings for many speakers (>220) from many raters (>160). We analyze listener preferences by correlating the resulting ranking with various acoustic and prosodic features. We also present a neural network that is able to model the complexity of listener preferences and the underlying temporal evolution of features. The recurrent neural network achieves remarkably high performance in estimating the pairwise decisions and an ablation study points toward the criticality of modeling temporal aspects in speech quality assessment.}, language = {en} } @inproceedings{TsaiBaumannPecuneetal., author = {Tsai, Vivian and Baumann, Timo and Pecune, Florian and Cassell, Justine}, title = {Faster Responses Are Better Responses: Introducing Incrementality into Sociable Virtual Personal Assistants}, series = {9th International Workshop on Spoken Dialogue System Technology}, volume = {579}, booktitle = {9th International Workshop on Spoken Dialogue System Technology}, editor = {D'Haro, Luis Fernando and Banchs, Rafael E. and Li, Haizhou}, publisher = {Springer Singapore}, address = {Singapore}, isbn = {978-981-13-9442-3}, issn = {1876-1119}, doi = {10.1007/978-981-13-9443-0_10}, pages = {111 -- 118}, abstract = {Speech-based interactive systems, such as virtual personal assistants, inevitably use complex architectures, with a multitude of modules working in series (or less often in parallel) to perform a task (e.g., giving personalized movie recommendations via dialog). Add modules for evoking and sustaining sociability with the user and the accumulation of processing latencies through the modules results in considerable turn-taking delays. We introduce incremental speech processing into the generation pipeline of the system to overcome this challenge with only minimal changes to the system architecture, through partial underspecification that is resolved as necessary. A user study with a sociable movie recommendation agent objectively diminishes turn-taking delays; furthermore, users not only rate the incremental system as more responsive, but also rate its recommendation performance as higher.}, language = {en} } @inproceedings{NayakBaumannBhattacharyaetal., author = {Nayak, Shravan and Baumann, Timo and Bhattacharya, Supratik and Karakanta, Alina and Negri, Matteo and Turchi, Marco}, title = {See me Speaking? Differentiating on Whether Words are Spoken On Screen or Off to Optimize Machine Dubbing}, series = {ICMI '20 Companion: Companion Publication of the 2020 International Conference on Multimodal Interaction, 25.10.2020 - 29.10.2020; Virtual Event Netherlands}, booktitle = {ICMI '20 Companion: Companion Publication of the 2020 International Conference on Multimodal Interaction, 25.10.2020 - 29.10.2020; Virtual Event Netherlands}, editor = {Truong, Khiet}, publisher = {Association for Computing Machinery}, address = {New York,NY,United States}, isbn = {9781450380027}, doi = {10.1145/3395035.3425640}, pages = {130 -- 134}, abstract = {Dubbing is the art of finding a translation from a source into a target language that can be lip-synchronously revoiced, i. e., that makes the target language speech appear as if it was spoken by the very actors all along. Lip synchrony is essential for the full-fledged reception of foreign audiovisual media, such as movies and series, as violated constraints of synchrony between video (lips) and audio (speech) lead to cognitive dissonance and reduce the perceptual quality. Of course, synchrony constraints only apply to the translation when the speaker's lips are visible on screen. Therefore, deciding whether to apply synchrony constraints requires an automatic method for detecting whether an actor's lips are visible on screen for a given stretch of speech or not. In this paper, we attempt, for the first time, to classify on- from off-screen speech based on a corpus of real-world television material that has been annotated word-by-word for the visibility of talking lips on screen. We present classification experiments in which we classify}, language = {en} } @inproceedings{GeislingerMildeBaumannetal., author = {Geislinger, Robert and Milde, Benjamin and Baumann, Timo and Biemann, Chris}, title = {Live Subtitling for BigBlueButton with Open-Source Software}, series = {INTERSPEECH 2021: (Show \& Tell Contribution), 30 August - 3 September, 2021, Brno, Czechia}, booktitle = {INTERSPEECH 2021: (Show \& Tell Contribution), 30 August - 3 September, 2021, Brno, Czechia}, address = {Brno, Czechia}, pages = {3319 -- 3320}, abstract = {We present an open source plugin for live subtitling in the popular open source video conferencing software BigBlueBut-ton. Our plugin decodes each speaker's audio stream separately and in parallel, thereby obliviating the need for speaker di-arization and seamlessly handling overlapped talk. Any Kaldi-compatible nnet3 model can be used with our plugin and we demonstrate it using freely available TDNN-HMM-based ASR models for English and German. Our subtitles can be used as they are (e.g., in loud environments) or can form the basis for further NLP processes. Our tool can also simplify the collection of remotely recorded multi-party dialogue corpora.}, language = {en} } @inproceedings{BaumannHusseinMeyerSickendieketal., author = {Baumann, Timo and Hussein, Hussein and Meyer-Sickendiek, Burkhard and Elbeshausen, Jasper}, title = {A Tool for Human-in-the-Loop Analysis and Exploration of (not only) Prosodic Classifications for Post-modern Poetry}, series = {Informatik 2019 : 50 Jahre Gesellschaft f{\"u}r Informatik Workshop-Beitr{\"a}ge Fachtagung vom 23.-26. September 2019 in Kassel}, booktitle = {Informatik 2019 : 50 Jahre Gesellschaft f{\"u}r Informatik Workshop-Beitr{\"a}ge Fachtagung vom 23.-26. September 2019 in Kassel}, editor = {Draude, Claude and Lange, Martin and Sick, Bernhard}, publisher = {Gesellschaft f{\"u}r Informatik}, address = {Bonn}, isbn = {978-3-88579-689-3}, pages = {151 -- 156}, abstract = {Data-based analyses are becoming more and more common in the Digital Humanities and tools are needed that focus human efforts on the most interesting and important aspects of exploration, analysis and annotation by using active machine learning techniques. We present our ongoing work on a tool that supports classification tasks for spoken documents (in our case: read-out post-modern poetry) using a neural networks-based classification backend and a web-based exploration and classification environment.}, language = {en} } @inproceedings{KarakantaBhattacharyaNayaketal., author = {Karakanta, Alina and Bhattacharya, Supratik and Nayak, Shravan and Baumann, Timo and Negri, Matteo and Turchi, Marco}, title = {The Two Shades of Dubbing in Neural Machine Translation}, series = {Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020): Barcelona, Spain (Online)}, booktitle = {Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020): Barcelona, Spain (Online)}, editor = {Scott, Donia and Bel, Nuria and Zong, Chengqing}, publisher = {International Committee on Computational Linguistics}, address = {Stroudsburg, PA, USA}, doi = {10.18653/v1/2020.coling-main.382}, pages = {4327 -- 4333}, abstract = {Dubbing has two shades; synchronisation constraints are applied only when the actor's mouth is visible on screen, while the translation is unconstrained for off-screen dubbing. Consequently, different synchronisation requirements, and therefore translation strategies, are applied depending on the type of dubbing. In this work, we manually annotate an existing dubbing corpus (Heroes) for this dichotomy. We show that, even though we did not observe distinctive features between on- and off-screen dubbing at the textual level, on-screen dubbing is more difficult for MT (-4 BLEU points). Moreover, synchronisation constraints dramatically decrease translation quality for off-screen dubbing. We conclude that, distinguishing between on-screen and off-screen dubbing is necessary for determining successful strategies for dubbing-customised Machine Translation.}, language = {en} } @inproceedings{FischerNaikLangedijketal., author = {Fischer, Kerstin and Naik, Lakshadeep and Langedijk, Rosalyn Melissa and Baumann, Timo and Jel{\´i}nek, Matouš and Palinko, Oskar}, title = {Initiating Human-Robot Interactions Using Incremental Speech Adaptation}, series = {HRI '21 Companion, Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction: March 8 - 11, 2021, Boulder CO, USA}, booktitle = {HRI '21 Companion, Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction: March 8 - 11, 2021, Boulder CO, USA}, editor = {Bethel, Cindy and Paiva, Ana}, publisher = {Association for Computing Machinery}, address = {New York, NY}, isbn = {9781450382908}, doi = {10.1145/3434074.3447205}, pages = {421 -- 425}, abstract = {In this paper, we present a study in which a robot initiates interactions with people passing by in an in-the-wild scenario. The robot adapts the loudness of its voice dynamically to the distance of the respective person approached, thus indicating who it is talking to. It furthermore tracks people based on information on body orientation and eye gaze and adapts the text produced based on people's distance autonomously. Our study shows that the adaptation of the loudness of its voice is perceived as personalization by the participants and that the likelihood that they stop by and interact with the robot increases when the robot incrementally adjusts its behavior.}, language = {en} } @article{GoeppelFrikelHaltmeier, author = {G{\"o}ppel, Simon and Frikel, J{\"u}rgen and Haltmeier, Markus}, title = {Feature Reconstruction from Incomplete Tomographic Data without Detour}, series = {Mathematics}, volume = {10}, journal = {Mathematics}, number = {8}, publisher = {MDPI}, doi = {10.3390/math10081318}, abstract = {In this paper, we consider the problem of feature reconstruction from incomplete X-ray CT data. Such incomplete data problems occur when the number of measured X-rays is restricted either due to limit radiation exposure or due to practical constraints, making the detection of certain rays challenging. Since image reconstruction from incomplete data is a severely ill-posed (unstable) problem, the reconstructed images may suffer from characteristic artefacts or missing features, thus significantly complicating subsequent image processing tasks (e.g., edge detection or segmentation). In this paper, we introduce a framework for the robust reconstruction of convolutional image features directly from CT data without the need of computing a reconstructed image first. Within our framework, we use non-linear variational regularization methods that can be adapted to a variety of feature reconstruction tasks and to several limited data situations. The proposed variational regularization method minimizes an energy functional being the sum of a feature dependent datafitting term and an additional penalty accounting for specific properties of the features. In our numerical experiments, we consider instances of edge reconstructions from angular under-sampled data and show that our approach is able to reliably reconstruct feature maps in this case.}, language = {en} } @inproceedings{BlankBrunnerFuhrmannetal., author = {Blank, M. and Brunner, Stefan and Fuhrmann, Thomas and Meier, Hans and Niemetz, Michael}, title = {Embedded Linux in engineering education}, series = {2015 IEEE Global Engineering Education Conference (EDUCON), 18-20 March 2015, Tallinn, Estonia}, booktitle = {2015 IEEE Global Engineering Education Conference (EDUCON), 18-20 March 2015, Tallinn, Estonia}, publisher = {IEEE}, doi = {10.1109/EDUCON.2015.7095964}, pages = {145 -- 150}, abstract = {With the availability of cost effective embedded Linux solutions and the increasing complexity of embedded devices because of growing calculation power and communication demand, Linux is getting increasingly interesting as an operating system for the design of embedded control solutions. This is the case for almost all technical applications in electrical engineering like energy distribution systems, high level communication, signal processing or industrial automation. In the engineering master courses at the OTH Regensburg, a lecture is offered introducing students to Linux with a strong focus on embedded applications. This paper describes the concept of the lecture including the laboratory set up and gives some examples of embedded Linux projects performed by students.}, language = {en} } @inproceedings{StudtWeissMottoketal., author = {Studt, Reimer and Weiß, Florian and Mottok, J{\"u}rgen and Weiss, Florian and Mottok, J{\"u}rgen}, title = {An engineering approach to developing lecture material for new study courses}, series = {2014 IEEE Global Engineering Education Conference (EDUCON), 3-5 April 2014, Istanbul, Turkey}, booktitle = {2014 IEEE Global Engineering Education Conference (EDUCON), 3-5 April 2014, Istanbul, Turkey}, publisher = {IEEE}, doi = {10.1109/EDUCON.2014.6826153}, pages = {592 -- 597}, abstract = {Professional software development is a complex task with many inputs and a complex output. In order to handle complex topics as software or complex engineering projects, structured processes as the V-model or iterative development processes exist. Similarly, the development of a software engineering lecture is a task with many inputs, and a complex output. A structured and methodological approach to the development of a lecture is presented, which applies the same principles as used in the development of software.}, language = {en} } @inproceedings{SchiekSetzpfandtBaronio, author = {Schiek, Roland and Setzpfandt, Frank and Baronio, Fabio}, title = {Akhmediev Breathers and Modulation Instability's Growth-Decay Cycle in Slab Waveguides}, series = {Nonlinear Optics : 15-19 July 2019, Waikoloa Beach, Hawaii, United States}, booktitle = {Nonlinear Optics : 15-19 July 2019, Waikoloa Beach, Hawaii, United States}, publisher = {OSA}, address = {Washington, D.C.}, isbn = {978-1-943580-62-0}, doi = {10.1364/nlo.2019.ntu2a.2}, abstract = {Optical film waveguides served as new platform for investigating Akhmediev Breathers. Using the interplay between third-order and cascaded second-order optical nonlinearities breathers and modulation instability cycles in a wide nonlinear regime were characterized.}, language = {en} } @misc{Schiek, author = {Schiek, Roland}, title = {On the experimental ex citation of modulation instability and Akhmediev breathers}, series = {CHAOS 2020, Proceedings, 13th Chaotic Modeling and Simulation, International Conference, 9 - 12 June, 2020, Florence, Italy,}, journal = {CHAOS 2020, Proceedings, 13th Chaotic Modeling and Simulation, International Conference, 9 - 12 June, 2020, Florence, Italy,}, language = {en} } @article{Groeger, author = {Gr{\"o}ger, Detlef}, title = {Construction of Locally Compact Near-Fields from p-Adic Division Algebras}, series = {Results in Mathematics}, volume = {75}, journal = {Results in Mathematics}, number = {4}, publisher = {Springer Nature}, doi = {10.1007/s00025-020-01290-5}, abstract = {The aim of this work is the construction of a new class of disconnected locally compact near-fields. They are all Dickson near-fields and derived from finite-dimensional division algebras over local fields by means of strong couplings with a finite Abelian Dickson group consisting of inner automorphisms.}, language = {en} } @article{Stein, author = {Stein, Oliver}, title = {Analytic properties of eisenstein series and standard L-Functions}, series = {Nagoya mathematical Journal}, volume = {244}, journal = {Nagoya mathematical Journal}, publisher = {CAMBRIDGE UNIV PRESS}, doi = {10.1017/nmj.2020.11}, pages = {168 -- 203}, abstract = {We prove a functional equation for a vector valued real analytic Eisenstein series transforming with the Weil representation of Sp(n, Z) on C[(L'/L)(n)]. By relating such an Eisenstein series with a real analytic Jacobi Eisenstein series of degree n, a functional equation for such an Eisenstein series is proved. Employing a doubling method for Jacobi forms of higher degree established by Arakawa, we transfer the aforementioned functional equation to a zeta function defined by the eigenvalues of a Jacobi eigenform. Finally, we obtain the analytic continuation and a functional equation of the standard L-function attached to a Jacobi eigenform, which was already proved by Murase, however in a different way.}, language = {en} } @article{BauerLauf, author = {Bauer, Ulrich and Lauf, Wolfgang}, title = {Conformal Mapping onto a Doubly Connected Circular Arc Polygonal Domain}, series = {Computational Methods and Function Theory}, volume = {19}, journal = {Computational Methods and Function Theory}, publisher = {Springer Nature}, doi = {10.1007/s40315-018-0256-0}, pages = {77 -- 96}, abstract = {This paper presents a construction principle for the Schwarzian derivative of conformal mappings from an annulus onto doubly connected domains bounded by polygons of circular arcs.}, language = {en} } @inproceedings{KaessGodefroidBorghoffetal., author = {K{\"a}ss, Sebastian and Godefroid, Marie and Borghoff, Vincent and Strahringer, Susanne and Westner, Markus and Plattfaut, Ralf}, title = {Towards a taxonomy of concepts describing IT outside the IT department}, series = {Australasian Conference on Information Systems 2021, Sydney}, booktitle = {Australasian Conference on Information Systems 2021, Sydney}, abstract = {Due to technological advances, IT is increasingly introduced and managed outside of (or even hidden from) an organisation's IT department. As a result, researchers and practitioners have created multiple concepts describing different facets and trends of this development. While the individual concepts typically focus on different aspects, there are overlaps between these concepts. This effect hampers research progress as it creates redundancies and separate streams of knowledge development. We propose a taxonomy of the concepts Lightweight IT, IT Consumerisation, Bring Your Own Device, Shadow IT, and Business-Managed IT to solve this research problem based on a systematic literature review. For this purpose, we derive characterising dimensions of each concept from existing studies and analyse literature according to the usage of terms. As a result, we can describe and delineate the concepts. Thus, we contribute a taxonomy of IT outside the IT department to improve the transfer of research results between research streams.}, language = {en} } @inproceedings{Schiek, author = {Schiek, Roland}, title = {Parameter Scans for Characterization of Nonlinear Beam Propagation}, series = {Proceedings OSA Nonlinear Optics 2021: 9-13 August 2021, Washington, DC, United States}, booktitle = {Proceedings OSA Nonlinear Optics 2021: 9-13 August 2021, Washington, DC, United States}, publisher = {Optica Publishing Group, OSA}, address = {Washington, D.C.}, isbn = {978-1-943580-97-2}, doi = {10.1364/nlo.2021.ntu1b.5}, abstract = {Intensity-dependent beam propagation inside nonlinear media is difficult to characterize without cutting back — and destroying — the sample. Observing the output dependent on system parameters can provide information on the beam dynamics along the path.}, language = {en} } @article{DrechslerKieslMeinfelderetal., author = {Drechsler, J{\"o}rg and Kiesl, Hans and Meinfelder, Florian and Raghunathan, Trivellore E. and Rubin, Donald B. and Schenker, Nathaniel and Zell, Elizabeth R.}, title = {In Memory of Professor Susanne R{\"a}ssler}, series = {Journal of Official Statistics}, volume = {35}, journal = {Journal of Official Statistics}, number = {1}, publisher = {de Gruyter}, doi = {10.2478/jos-2019-0013}, pages = {285 -- 286}, language = {en} } @article{SetzpfandtSohlerSchieketal., author = {Setzpfandt, Frank and Sohler, Wolfgang and Schiek, Roland and Pertsch, Thomas}, title = {Nonlinear coupling in discrete optical waveguide arrays with quadratic nonlinearity}, series = {Physical Review A}, volume = {92}, journal = {Physical Review A}, number = {4}, publisher = {American Physical Society}, doi = {10.1103/PhysRevA.92.043832}, abstract = {We demonstrate nonlinear coupling in a discrete optical system. This is achieved in waveguide arrays with quadratic nonlinearity, where the symmetries of the nonlinearly interacting waveguide modes are used to suppress the usually dominating nonlinear effects within individual waveguides. We derive a mathematical model to describe the nonlinear coupling in such waveguide arrays and show experimentally the profound effects of this nonlinear coupling mechanism on second-harmonic generation.}, language = {en} } @article{FreilingGrimmGrosspietschetal., author = {Freiling, Felix and Grimm, R{\"u}diger and Großpietsch, Karl-Erwin and Keller, Hubert B. and Mottok, J{\"u}rgen and M{\"u}nch, Isabel and Rannenberg, Kai and Saglietti, Francesca}, title = {Technische Sicherheit und Informationssicherheit. Unterschiede und Gemeinsamkeiten}, series = {Informatik-Spektrum}, volume = {37}, journal = {Informatik-Spektrum}, number = {1}, publisher = {Springer}, doi = {10.1007/s00287-013-0748-2}, pages = {14 -- 24}, language = {de} } @article{YuanGeisslerShaoetal., author = {Yuan, Jing and Geissler, Christian and Shao, Weijia and Lommatzsch, Andreas and Jain, Brijnesh}, title = {When algorithm selection meets Bi-linear Learning to Rank: accuracy and inference time trade off with candidates expansion}, series = {International Journal of Data Science and Analytics}, journal = {International Journal of Data Science and Analytics}, publisher = {Springer Nature}, doi = {10.1007/s41060-020-00229-x}, pages = {17}, abstract = {Algorithm selection (AS) tasks are dedicated to find the optimal algorithm for an unseen problem instance. With the knowledge of problem instances' meta-features and algorithms' landmark performances, Machine Learning (ML) approaches are applied to solve AS problems. However, the standard training process of benchmark ML approaches in AS either needs to train the models specifically for every algorithm or relies on the sparse one-hot encoding as the algorithms' representation. To escape these intermediate steps and form the mapping function directly, we borrow the learning to rank framework from Recommender System (RS) and embed the bi-linear factorization to model the algorithms' performances in AS. This Bi-linear Learning to Rank (BLR) has proven to work with competence in some AS scenarios and thus is also proposed as a benchmark approach. Thinking from the evaluation perspective in the modern AS challenges, precisely predicting the performance is usually the measuring goal. Though approaches' inference time also needs to be counted for the running time cost calculation, it's always overlooked in the evaluation process. The multi-objective evaluation metric Adjusted Ratio of Root Ratios (A3R) is therefore advocated in this paper to balance the trade-off between the accuracy and inference time in AS. Concerning A3R, BLR outperforms other benchmarks when expanding the candidates range to TOP3. The better effect of this candidates expansion results from the cumulative optimum performance during the AS process. We take the further step in the experimentation to represent the advantage of such TOPK expansion, and illustrate that such expansion can be considered as the supplement for the convention of TOP1 selection during the evaluation process.}, language = {en} } @article{Jain, author = {Jain, Brijnesh}, title = {Sufficient conditions for the existence of a sample mean of time series under dynamic time warping}, series = {Annals of Mathematics and Artificial Intelligence}, volume = {88}, journal = {Annals of Mathematics and Artificial Intelligence}, publisher = {Springer Nature}, doi = {10.1007/s10472-019-09682-2}, pages = {313 -- 346}, abstract = {Time series averaging is an important subroutine for several time series data mining tasks. The most successful approaches formulate the problem of time series averaging as an optimization problem based on the dynamic time warping (DTW) distance. The existence of an optimal solution, called sample mean, is an open problem for more than four decades. Its existence is a necessary prerequisite to formulate exact algorithms, to derive complexity results, and to study statistical consistency. In this article, we propose sufficient conditions for the existence of a sample mean. A key result for deriving the proposed sufficient conditions is the Reduction Theorem that provides an upper bound for the minimum length of a sample mean.}, language = {en} } @article{BrillFluschnikFroeseetal., author = {Brill, Markus and Fluschnik, Till and Froese, Vincent and Jain, Brijnesh and Niedermeier, Rolf and Schultz, David}, title = {Exact mean computation in dynamic time warping spaces}, series = {Data Mining and Knowledge Discovery}, volume = {33}, journal = {Data Mining and Knowledge Discovery}, publisher = {Springer Nature}, doi = {10.1007/s10618-018-0604-8}, pages = {252 -- 291}, abstract = {Averaging time series under dynamic time warping is an important tool for improving nearest-neighbor classifiers and formulating centroid-based clustering. The most promising approach poses time series averaging as the problem of minimizing a Fr{\´e}chet function. Minimizing the Fr{\´e}chet function is NP-hard and so far solved by several heuristics and inexact strategies. Our contributions are as follows: we first discuss some inaccuracies in the literature on exact mean computation in dynamic time warping spaces. Then we propose an exponential-time dynamic program for computing a global minimum of the Fr{\´e}chet function. The proposed algorithm is useful for benchmarking and evaluating known heuristics. In addition, we present an exact polynomial-time algorithm for the special case of binary time series. Based on the proposed exponential-time dynamic program, we empirically study properties like uniqueness and length of a mean, which are of interest for devising better heuristics. Experimental evaluations indicate substantial deficits of state-of-the-art heuristics in terms of their output quality.}, language = {en} } @article{Stein, author = {Stein, Oliver}, title = {The Fourier expansion of Hecke operators for vector-valued modular forms}, series = {Functiones et Approximatio Commentarii Mathematici}, volume = {52}, journal = {Functiones et Approximatio Commentarii Mathematici}, number = {2}, publisher = {Adam Mickiewicz University, Faculty of Mathematics and Computer Science}, address = {Poznań}, issn = {2080-9433}, doi = {10.7169/facm/2015.52.2.4}, pages = {229 -- 252}, abstract = {We compute the Fourier expansion of Hecke operators on vector-valued modular forms for the Weil representation associated to a lattice L. The Hecke operators considered in this paper include operators T(p^2l) where p is a prime dividing the level of the lattice L. Additionally, an explicit formula for a general type of Gauss sum associated to a lattice L drops out as a by-product.}, language = {en} } @inproceedings{HeldWestner, author = {Held, Tobias and Westner, Markus}, title = {IT Business Value Measurement and Communication among German CIOs: A Conceptual Framework}, series = {2022 IEEE 24th Conference on Business Informatics (CBI): 15-17 June 2022, Amsterdam, Netherlands}, booktitle = {2022 IEEE 24th Conference on Business Informatics (CBI): 15-17 June 2022, Amsterdam, Netherlands}, publisher = {IEEE}, doi = {10.1109/CBI54897.2022.00023}, pages = {146 -- 155}, abstract = {This paper applies design science research methodology to iteratively develop a framework for measuring and communicating IT business value from a CIO perspective. The framework design is based on analysis and integration of literature combined with empirical findings. The framework was evaluated by CIO interviews and a practical feasibility study. The results show that IT business value can be measured and communicated using our framework by applying six consecutive process steps. Thereby, IT business value is not a single number but a set of quantitative and qualitative metrics relevant to stakeholders. Our framework represents a novel and integrated approach on how CIOs can select appropriate metrics, measure, and communicate IT business value to stakeholders. In addition, the paper provides insights for CIOs on how to be successful in IT business value management.}, language = {en} } @inproceedings{SchildgenKrueckDessloch, author = {Schildgen, Johannes and Kr{\"u}ck, Yannick and Deßloch, Stefan}, title = {Transformations on Graph Databases for Polyglot Persistence with NotaQL}, series = {Datenbanksysteme f{\"u}r Business, Technologie und Web, 17. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssyteme" (DBIS) : 06.-10.03.2017 in Stuttgart, Deutschland (BTW 2017)}, booktitle = {Datenbanksysteme f{\"u}r Business, Technologie und Web, 17. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssyteme" (DBIS) : 06.-10.03.2017 in Stuttgart, Deutschland (BTW 2017)}, number = {CD-ROM}, editor = {Mitschang, Bernhard and Nicklas, Daniela and Leymann, Frank and Sch{\"o}ning, Harald and Herschel, Melanie and Teubner, Jens and H{\"a}rder, Theo and Kopp, Oliver and Wieland, Matthias}, publisher = {Gesellschaft f{\"u}r Informatik, Bonn}, pages = {83 -- 102}, language = {en} } @article{SchleglRobatzekKuceraetal., author = {Schlegl, Peter and Robatzek, Patrick and Kucera, Markus and Volbert, Klaus and Waas, Thomas}, title = {Performance analysis of mobile radio for automatic control in smart grids}, series = {International Journal of Advancements in Electronics and Electrical Engineering}, volume = {4}, journal = {International Journal of Advancements in Electronics and Electrical Engineering}, number = {1}, issn = {2319-7498}, pages = {69 -- 75}, abstract = {In the context of a "Smart Grid" research project, together with industrial partners, the OTH-Regensburg realized an intelligent medium-voltage grid in the local area. Goal was to improve the current voltage regulation and to counter the problems with inconsistent energy feed-in of decentralized renewable energy producers. In this paper we discuss the possibilities of using 3rd generation (3G) cellular networks (UMTS) as basic technology to communicate the voltage-levels within a medium-voltage grid. We build an experimental hardware setup to generate data-traffic as specified for the smart grid. By analyzing the performance of 3G cellular networks in terms of transmission latency and rate of failure, we tried to evaluate the usability of this technology for such critical data exchange. Though mobile communication in its structure is not specified for the use of transmitting such infrastructure critical data, the results show a promising high reliability with low transmission latency. The experiments served just to test a fragment of the conditions of use in a real scenario. An expanded test scope is needed to further analyze the performance of mobile radio for automatic control in smart grids. In the end the results discussed in this paper led to a successful prototype of an intelligent medium-voltage grid with mobile radio as communication technology}, language = {en} }