@inproceedings{Hoefig2012, author = {H{\"o}fig, Kai}, title = {Failure-dependent timing analysis-a new methodology for probabilistic worst-case execution time analysis}, series = {International GI/ITG Conference on Measurement, Modelling, and Evaluation of Computing Systems and Dependability and Fault Tolerance.}, booktitle = {International GI/ITG Conference on Measurement, Modelling, and Evaluation of Computing Systems and Dependability and Fault Tolerance.}, publisher = {Springer}, address = {Berlin, Heidelberg}, pages = {61 -- 75}, year = {2012}, abstract = {Embedded real-time systems are growing in complexity, which goes far beyond simplistic closed-loop functionality. Current approaches for worst-case execution time (WCET) analysis are used to verify the deadlines of such systems. These approaches calculate or measure the WCET as a single value that is expected as an upper bound for a system's execution time. Overestimations are taken into account to make this upper bound a safe bound, but modern processor architectures expand those overestimations into unrealistic areas. Therefore, we present in this paper how of safety analysis model probabilities can be combined with elements of system development models to calculate a probabilistic WCET. This approach can be applied to systems that use mechanisms belonging to the area of fault tolerance, since such mechanisms are usually quantified using safety analyses to certify the system as being highly reliable or safe. A tool prototype implementing this approach is also presented which provides reliable safe upper bounds by performing a static WCET analysis and which overcomes the frequently encountered problem of dependence structures by using a fault injection approach.}, language = {en} } @inproceedings{Hoefig2011, author = {H{\"o}fig, Kai}, title = {FDTA-A Tool Chain for Failure-Dependent Timing Analysis}, series = {Proc. of the 11th International Workshop on Worst-Case Execution Time Analysis}, booktitle = {Proc. of the 11th International Workshop on Worst-Case Execution Time Analysis}, year = {2011}, abstract = {Embedded real-time systems are growing in complexity, which goes far beyond simplistic closedloop functionality. Current approaches of worst-case execution time (WCET) analysis are used to verify deadlines of such systems, especially when they are safety critical. These approaches calculate or measure WCET as a single value that is expected as an upper bound for a system's execution time. Overestimations are taken into account to make this upper bound a safe bound, but modern processor architectures with caches, multi-threading, and instruction pipelines often expand those overestimations for safe upper bounds into unrealistic areas. Some approaches try to overcome this problem by calculating multiple upper bounds and argue that each single upper bound will hold for a certain probability (probabilistic worst-case execution time). Even though some of them tackle the problem of obtaining reliable probabilistic values for such upper bounds, more effort is required. Therefore, we present in this paper how probabilities of safety analysis models can be combined with elements of system development models to calculate a probabilistic worst-case execution time. This approach can be applied to systems that use mechanisms belonging to the area of fault tolerance, since such mechanisms are usually quantified in safety analyses to certify the system as being highly reliable or safe.}, language = {en} } @inproceedings{HoefigArmbrusterSchmidt2014, author = {H{\"o}fig, Kai and Armbruster, Michael and Schmidt, Reiner}, title = {A vehicle control platform as safety element out of context.}, series = {HiPEAC Computing Systems Week, Barcelona, Spain, May 2014.}, booktitle = {HiPEAC Computing Systems Week, Barcelona, Spain, May 2014.}, year = {2014}, language = {en} } @inproceedings{HoefigDomis2011, author = {H{\"o}fig, Kai and Domis, Dominik}, title = {Failure-Dependent execution time analysis}, series = {Proceedings of the Joint ACM SIGSOFT Conference-QoSA and ACM SIGSOFT Symposium-ISARCS on Quality of Software Architectures-QoSA and Architecting Critical Systems-ISARCS, Boulder, Colorado, USA, June 2011.}, booktitle = {Proceedings of the Joint ACM SIGSOFT Conference-QoSA and ACM SIGSOFT Symposium-ISARCS on Quality of Software Architectures-QoSA and Architecting Critical Systems-ISARCS, Boulder, Colorado, USA, June 2011.}, publisher = {ACM}, address = {New York, NY, USA}, pages = {115 -- 122}, year = {2011}, abstract = {The growing complexity of safety-critical embedded systems is leading to an increased complexity of safety analysis models. Often used fault tolerance mechanisms have complex failure behavior and produce overhead compared to systems without such mechanisms. The question arises whether the overhead for fault tolerance is acceptable for the increased safety of a system. Manually modeling the timing behavior is cost intensive and error prone. Current approaches of safety analysis and execution time analysis are not able to reflect the timing behavior of complex mechanisms according to failures. In this paper, we describe an approach that combines safety analysis models with execution times to extract different execution times for different failure conditions. This provides a detailed view on the safety behavior in combination with the produced overhead and allows to find and certify appropriate fault tolerance mechanisms.}, language = {en} } @misc{HoefigZeller2016, author = {H{\"o}fig, Kai and Zeller, Marc}, title = {Automated Qualification of a Safety Critical System}, year = {2016}, abstract = {A method for automated qualification of a safety critical system including a plurality of components is provided. A functional safety behavior of each component is represented by an associated component fault tree element. The method includes automatically performing a failure port mapping of output failure modes to input failure modes of component fault tree elements based on a predetermined generic fault type data model stored in a database.}, language = {en} } @book{Jarz1997, author = {Jarz, Ewald}, title = {Entwicklung multimedialer Systeme}, publisher = {Gabler}, address = {Wiesbaden}, isbn = {3-8244-6523-X}, publisher = {Technische Hochschule Rosenheim}, pages = {361}, year = {1997}, abstract = {Die Arbeit ist eine Anleitung zur Planung und Erstellung von IT-Systemen, die auch Filme, Sprache, Musik, Animationen und virtuelle Welten - also die gesamte Palette multimedialer Darstellungen - beinhalten. Solche Programme werden haupts{\"a}chlich in drei Bereichen eingesetzt: Im Spielebereich (z.B. Autorennen, Erlebnisspiele), im Aus- und Weiterbildungsbereich (z.B. multimediale Lernprogramme) und im Bereich von elektronisch unterst{\"u}tzten Informationssystemen (z.B. Pr{\"a}sentationen, Produktvorstellungen und Produktkataloge u.a. auch auf CD-ROM oder Kiosksysteme wie etwa Informationsterminals auf Messen u.{\"a}.). Die Arbeit besch{\"a}ftigt sich vorwiegend mit Lernsystemen. Das Schwierige an der Verwendung multimedialer Darstellungen wie Film, Musik usw. ist, dass in die "trockene" Programmierung Aspekte wie Regie, Dramaturgie, psychologische und didaktische Aspekte einfließen. Daher ist die interdisziplin{\"a}re Sichtweise bei der Entwicklung multimedialer Systeme besonders wichtig. Die Arbeit betrachtet die Problematik also nicht techniklastig (obwohl nat{\"u}rlich die technischen Aspekte nicht außer Acht gelassen werden), sondern nutzerorientiert. Die Arbeit ist f{\"u}r drei Bereiche bedeutend: erstens f{\"u}r den Bereich der Wissenschaft(stheorie), zweitens f{\"u}r den Aus- und Weiterbildungssektor und drittens f{\"u}r die Entwickler von multimedialen Systemen. Aus der Sicht der Wissenschaft liefert die Arbeit eine klare Einteilung f{\"u}r multimediale Arbeitsbereiche. M{\"o}gliche k{\"u}nftige Forschungsbereiche werden aufgezeigt und begriffliche Unklarheiten offengelegt und ausger{\"a}umt. Weiters wird die interdisziplin{\"a}re Bandbreite der Thematik geschildert und damit eine umfassende Darstellung der Problematik vorgenommen. In diesem Sinn kann die Arbeit fast als Lexikon gesehen werden. Aus der Sicht des Aus- und Weiterbildungssektors dient diese Arbeit als Zusammenfassung bestehender Lernkonzepte, in der ein eigenst{\"a}ndiger, einfacher Raster in Hinblick auf multimediale Systeme entwickelt wird. Dabei werden Erfahrungen aus mehreren multimedialen Programmen eingearbeitet, die vom Autor am Institut f{\"u}r Wirtschaftsinformatik (mit)entwickelt und evaluiert worden sind. Eine Erkenntnis ist, dass der Wissensstand des Benutzers auf dem Lerngebiet eine entscheidende Rolle spielt. Lernsysteme f{\"u}r Anf{\"a}nger m{\"u}ssen anders gestaltet werden als f{\"u}r Fortgeschrittene. Das wie wird in der Arbeit beschrieben. Aus der Sicht der Entwickler von multimedialen Systemen ist die Arbeit von Bedeutung, da sie die Unterschiede bei der Entwicklung im Vergleich zu traditionellen Programmen herausarbeitet und daf{\"u}r eine Vorgangsweise anbietet. Die Vorgangsweise ist eine Art multimediales Drehbuch, das als Storyboard bezeichnet wird. In der Arbeit wird beschrieben wie die einzelnen dramaturgischen, didaktischen und psychologischen Aspekte in das Storyboard eingearbeitet werden und letztlich das System in einem entsprechenden Umfeld eingesetzt werden kann.}, language = {de} } @article{WenningerBayerlSchmidtetal.2019, author = {Wenninger, Marc and Bayerl, Sebastian P. and Schmidt, Jochen and Riedhammer, Korbinian}, title = {Timage - A Robust Time Series Classification Pipeline}, series = {Artificial Neural Networks and Machine Learning - ICANN 2019: Text and Time Series. ICANN 2019. Lecture Notes in Computer Science}, volume = {11730}, journal = {Artificial Neural Networks and Machine Learning - ICANN 2019: Text and Time Series. ICANN 2019. Lecture Notes in Computer Science}, publisher = {Springer}, address = {Cham}, year = {2019}, abstract = {Time series are series of values ordered by time. This kind of data can be found in many real world settings. Classifying time series is a difficult task and an active area of research. This paper investigates the use of transfer learning in Deep Neural Networks and a 2D representation of time series known as Recurrence Plots. In order to utilize the research done in the area of image classification, where Deep Neural Networks have achieved very good results, we use a Residual Neural Networks architecture known as ResNet. As preprocessing of time series is a major part of every time series classification pipeline, the method proposed simplifies this step and requires only few parameters. For the first time we propose a method for multi time series classification: Training a single network to classify all datasets in the archive with one network. We are among the first to evaluate the method on the latest 2018 release of the UCR archive, a well established time series classification benchmarking dataset.}, language = {en} } @article{WenningerStecherSchmidt2019, author = {Wenninger, Marc and Stecher, Dominik and Schmidt, Jochen}, title = {SVM-Based Segmentation of Home Appliance Energy Measurements}, series = {Proceedings 8th IEEE International Conference on Machine Learning and Applications -ICMLA 2019}, journal = {Proceedings 8th IEEE International Conference on Machine Learning and Applications -ICMLA 2019}, pages = {1666 -- 1670}, year = {2019}, abstract = {Generating a more detailed understanding of domestic electricity demand is a major topic for energy suppliers and householders in times of climate change. Over the years there have been many studies on consumption feedback systems to inform householders, disaggregation algorithms for Non-Intrusive-Load-Monitoring (NILM), Real-Time-Pricing (RTP) to promote supply aware behavior through monetary incentives and appliance usage prediction algorithms. While these studies are vital steps towards energy awareness, one of the most fundamental challenges has not yet been tackled: Automated detection of start and stop of usage cycles of household appliances. We argue that most research efforts in this area will benefit from a reliable segmentation method to provide accurate usage information. We propose a SVM-based segmentation method for home appliances such as dishwashers and washing machines. The method is evaluated using manually annotated electricity measurements of five different appliances recorded over two years in multiple households.}, language = {en} } @book{Schmidt2019, author = {Schmidt, Jochen}, title = {Grundkurs Informatik - Das {\"U}bungsbuch: 148 Aufgaben mit L{\"o}sungen}, edition = {1}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3658259440}, publisher = {Technische Hochschule Rosenheim}, pages = {196}, year = {2019}, language = {de} } @book{BenekenErnstSchmidt2015, author = {Beneken, Gerd and Ernst, H. and Schmidt, Jochen}, title = {Grundkurs Informatik: Grundlagen und Konzepte f{\"u}r die erfolgreiche IT-Praxis - Eine umfassende, praxisorientierte Einf{\"u}hrung (Auflage von 2015)}, publisher = {Springer Vieweg}, address = {Berlin}, publisher = {Technische Hochschule Rosenheim}, year = {2015}, abstract = {Das Buch bietet eine umfassende und praxisorientierte Einf{\"u}hrung in die wesentlichen Grundlagen und Konzepte der Informatik. Es umfasst den Stoff, der typischerweise in den ersten Semestern eines Informatikstudiums vermittelt wird, vertieft Zusammenh{\"a}nge, die dar{\"u}ber hinausgehen und macht sie verst{\"a}ndlich. Die Themenauswahl orientiert sich an der langfristigen Relevanz f{\"u}r die praktische Anwendung. Praxisnah und aktuell werden die Inhalte f{\"u}r Studierende der Informatik und verwandter Studieng{\"a}nge sowie f{\"u}r im Beruf stehende Praktiker vermittelt. Die vorliegende f{\"u}nfte Auflage wurde grundlegend {\"u}berarbeitet und aktualisiert.}, language = {de} } @book{HammerschallBeneken2013, author = {Hammerschall, Ulrike and Beneken, Gerd}, title = {Software Requirements (Pearson Studium - IT)}, publisher = {Pearson Studium}, address = {Hallbergmoos}, publisher = {Technische Hochschule Rosenheim}, year = {2013}, abstract = {Das Lehrbuch Software Requirements von Ulrike Hammerschall und Gerd Beneken f{\"u}hrt in die Grundkonzepte des Requirements Engineering ein und zeigt anhand vieler anschaulicher Beispiele, wie man systematisch und methodisch bei der Ermittlung, Dokumentation, Spezifikation, Modellierung, Validierung und Verwaltung von Software Requirements vorgeht. Mit seinem Inhalt und didaktisch wertvollem Aufbau richtet sich das Buch an Studierende der Fachrichtung Informatik und Wirtschaftsinformatik, sowie aller verwandten Fachrichtungen, die sich mit den Themen Software Engineering oder Requirements Engineering besch{\"a}ftigen. Software Requirements sind die Anforderungen der Anwender an die Funktionalit{\"a}t eines geplanten Software-Systems. Requirements Engineering ist der Prozess zur methodischen Erhebung und Beschreibung der Anforderungen. Die Kunst eines guten Requirements Engineerings ist die Entwicklung einer stabilen Anforderungsbasis als zuverl{\"a}ssige Grundlage f{\"u}r die weitere Entwicklung der Software. Das vorliegende Buch f{\"u}hrt in die Grundkonzepte des Requirements Engineering ein und zeigt anhand vieler Beispiele, wie man systematisch und methodisch bei der Ermittlung, Dokumentation, Spezifikation, Modellierung, Validierung und Verwaltung von Software Requirements vorgeht. Ausf{\"u}hrliche Methodenbeschreibungen dienen zur Erl{\"a}uterung und ein durchg{\"a}ngiges Fallbeispiel hilft dem Leser die Anwendung der Methoden nachzuvollziehen. Mit Hilfe der {\"U}bungen am Ende jedes Kapitels, k{\"o}nnen die Methoden selbst einge{\"u}bt werden. Neben dem klassischen Dokument-getriebenen Requirements Engineering besch{\"a}ftigt sich das Buch mit den Methoden des agilen Requirements Engineering und vergleicht die beiden Ans{\"a}tze. Zus{\"a}tzlich bietet das Buch einen Blick {\"u}ber den Tellerrand und betrachtet die Schnittstellen des Requirements Engineerings zu anderen Teilprozessen im Entwicklungsprozess. Das Buch richtet sich an Studierende der Fachrichtung Informatik und Wirtschaftsinformatik, sowie aller verwandten Fachrichtungen, die sich mit den Themen Software Engineering oder Requirements Engineering besch{\"a}ftigen. - Der RE-Prozess, Vorgehen und Methodik. - Anforderungsermittlung, -dokumentation und -spezifikation. - Querschnittliche Aufgaben wie Validierung, Modellierung und Management von Anforderungen - Agiles RE, Vorgehen und Methodik. - Schnittstellen zu benachbarten Teilprozessen (Projektmanagement, Qualit{\"a}tsmanagement, Software-Architektur) sowie zum Usability Engineering. - Einf{\"u}hrung und Verbesserung des Requirements Engineering Prozesses in einer Organisation.}, language = {de} } @inproceedings{BenekenFeindorTurmayr2008, author = {Beneken, Gerd and Feindor, R. and Turmayr, J.}, title = {Integrierte Werkzeugunterst{\"u}tzung f{\"u}r kleine Projekte: Der Rosenheimer Team-Server}, series = {3. Workshop: Vorgehensmodelle in der Praxis - Werkzeuge und Anwendung (TUM)}, booktitle = {3. Workshop: Vorgehensmodelle in der Praxis - Werkzeuge und Anwendung (TUM)}, year = {2008}, abstract = {Aktuelle Projekte werden nur noch selten von einem einzigen Team an einem einzigen Standort bearbeitet. Um verteilt arbeitende Teams, Auftrag- und Unterauftragnehmer zu koordinieren, ist einerseits ein abgestimmtes Vorgehen notwendig, andererseits m{\"u}ssen Projekte in solchen Szenarios durch Werkzeuge unterst{\"u}tzt werden. Die problemorientierte und organisationsspezifische Integration von Werkzeugen und Vorgehensmodellen ist ein wesentliches Erfolgskriterium f{\"u}r Organisationen und ihre Projekte. Werkzeuge k{\"o}nnen Anwender unterst{\"u}tzen und durch vorgegebene Prozesse wie z.B. Risikomanagement oder Berichtswesen f{\"u}hren. Eine nahtlose Integration eines Vorgehensmodells in eine gegebene und akzeptierte Werkzeugumgebung kann sich positiv auf den Erfolg von Prozessanpassungen auswirken. Effizienzsteigerungen, bspw. durch die automatische Generierung von Vorlagen oder Dokumentation, machen Werkzeugintegrierte Prozesse auch f{\"u}r Entwickler interessant. Auf der anderen Seite m{\"u}ssen Projektspezifische Anforderungen an Werkzeuge und Prozesse ber{\"u}cksichtigt werden, die eine Flexibilit{\"a}t in der Anwendung und Benutzung erforderlich machen. Dieser 3. Workshop diskutiert in Fortsetzung der Workshops Formalisierung und Anwendung sowie Reife und Qualit{\"a}t unterschiedliche und facettenreiche Fragen, die sich hinsichtlich der Werkzeugunterst{\"u}tzung und der werkzeuggef{\"u}hrten Anwendung von Vorgehensmodellen ergeben. Insbesondere die semi- und vollautomatische Integration von Vorgehensmodellen, die Generierung von Arbeitsumgebungen und Optionen zur Anwenderunterst{\"u}tzung und Anwenderf{\"u}hrung spielen hier zentrale Rollen. Im Zentrum des Workshops steht der Lifecycle von Vorgehensmodellen mit dem Schwerpunkt der Operationalisierung durch Werkzeuge und der gef{\"u}hrten/unterst{\"u}tzten Anwendung. Von besonderem Interesse sind Fragen nach der Konzeption und Durchf{\"u}hrung von Werkzeugen und Anwenderunterst{\"u}tzung im Kontext verschiedener Vorgehensmodelle, wie bspw. dem V-Modell XT, Scrum, Prince2, RUP, XP. Themen{\"u}berblick: Der 1-t{\"a}ige Workshop zielt im Wesentlichen auf folgende Themen: Verbesserung der Akzeptanz von Vorgehensmodellen Werkzeugunterst{\"u}tzte Prozesseinf{\"u}hrung: Einf{\"u}hrung und Einf{\"u}hrbarkeit mithilfe von Werkzeugen Etablierung und Durchsetzung, Do's und Dont's Kontinuierliche werkzeugunterst{\"u}tzte Prozessverbesserung Kosten und Nutzen, Abh{\"a}ngigkeiten, Vor- und Nachteile Werkzeugunterst{\"u}tzung bei der Projektdurchf{\"u}hrung Lose gekoppelte Werkzeuglandschaften vs. integrierte Tools Werkzeugunterst{\"u}tzte Planung, Steuerung von Agilen Projekten Unterst{\"u}tzung f{\"u}r kleine, große und verteilte Teams Werkzeugunterst{\"u}tzung bei Auswahl, Anpassung und Tailoring Grenzen der Werkzeugunterst{\"u}tzung Formalisierung und Werkzeugunterst{\"u}tzung von Prozessen und Prozessschritten Vorgehens- und Reifegradmodelle: V-Model XT, XP, CMMI, RUP, Scrum etc.}, language = {de} } @inproceedings{BenekenMarschallRausch2005, author = {Beneken, Gerd and Marschall, F. and Rausch, A.}, title = {A Model Framework Weaving Approach, In: Proceedings of the First Workshop on Models and Aspects - Handling Crosscutting Concerns in MDSD at the 19th European Conference on Object-Oriented Programming (ECOOP 2005)}, series = {19th European Conference on Object-Oriented Programming (ECOOP 2005)}, booktitle = {19th European Conference on Object-Oriented Programming (ECOOP 2005)}, year = {2005}, abstract = {Nowadays, in software development usually various models and description fragments are created. Some of these artifacts describe the core of the application, such as the data model or the user interaction model. Other artifacts describe cross-cutting concerns, such as security or the requirement: "every change of data has to be confirmed by the user, before it is written into the database". During the development process these artifacts are combined, transformed, and finally implemented manually or even automatically. For instance a designer may combine a model of a dialog component specifying an action, that changes data, with a common description of a generic confirm dialog. The integrated dialog description may be afterwards implemented by a programmer. The manual combination of both artifacts and the transformation of the combined description into code are errorprone and hard to change. Industry basically tests or actually uses two approaches for the combination today: 1. At the level of code and execution Aspect-Oriented Programming (AOP) is used [KLM+97]. An aspect defines a cross-cutting concern and the weaving instructions. A code weaver provides the actual weaving at compile or runtime. 2. At the level of design models and analysis models Model-Driven Software Development (MDSD) is used [KWB03]. A model in MDSD is a first class development artifact. Thus models are significantly more abstract than the implementation of code. However, these models cannot be executed. Hence, a abstract model is transformed into another, typically more detailed. A series of such transformations results in executable code. Thereby, a model transformer or a code generator reads some of the artifacts. The other artifacts and the combination rules are implemented in transformation rules or code generation templates (or somewhere else in the transformation / generation approach).}, language = {en} } @inproceedings{SeifertBenekenBaehr2004, author = {Seifert, T. and Beneken, Gerd and Baehr, N.}, title = {Engineering Long-Lived Applications Using MDA}, series = {Intl. Conference on Software Engineering and Applications, pp. 241-246, Cambridge}, booktitle = {Intl. Conference on Software Engineering and Applications, pp. 241-246, Cambridge}, year = {2004}, abstract = {Creating long-lived software systems requires a technol ogy to build systems with good maintainability. One of the core ideas of the Model Driven Architecture (MDA) is to ease the change of the run-time platform by raising the level of abstraction in which just the business aspects are modelled, and by separating business aspects from techni cal issues and implementation details. This article anal yses the MDA approach with respect to maintainability. We argue that MDA systems will become even harder to maintain because the maintainability depends on the sys tem's (development) environment. MDA, UML and other base technologies are still under development, therefore the tools will change considerably. While the MDA possibly eases the change of the run-time platform, we show that it is quite difficult to exchange a link in the development tool chain. Our argumentation is based on the general proper ties of software evolution and the dependency chains in the development and run-time environments. It is backed by experiences with MDA development as well as by analo gies to general maintenance experiences.}, language = {en} } @inproceedings{BenekenSeifertBaehretal.2004, author = {Beneken, Gerd and Seifert, T. and Baehr, N. and Hanschke, I. and Rauch, O.}, title = {Referenzarchitekturen und MDA, In INFORMATIK 2004 - Informatik verbindet}, series = {Beitr{\"a}ge der 34. Jahrestagung der Gesellschaft f{\"u}r Informatik e.V.}, booktitle = {Beitr{\"a}ge der 34. Jahrestagung der Gesellschaft f{\"u}r Informatik e.V.}, year = {2004}, abstract = {Dieser Beitrag beschreibt, wie Referenzarchitekturen die MDA nutzbar machen. Die Referenzarchitekturen liefern dabei die konzeptionelle Unterst{\"u}tzung f{\"u}r die Konstruktion und Implementierung von Software und die MDA bietet den Rahmen f{\"u}r eine Werkzeugunterst{\"u}tzung. Die praktische Umsetzbarkeit wird mit dem OpenSource Framework AndroMDA und einer Referenzarchitektur der Firma iteratec GmbH gezeigt.}, language = {de} } @inproceedings{BenekenHammerschallBroyetal.2003, author = {Beneken, Gerd and Hammerschall, U. and Broy, M. and Cengarle, M.V. and J{\"u}rjens, J. and Pretschner, A. and Rumpe, B. and Sch{\"o}nmakers, M.}, title = {Componentware - State of the Art, Background Paper for the Understanding Components}, series = {Workshop of the CUE Initiative at the Univerita Ca Foscari di Venezia Venice}, booktitle = {Workshop of the CUE Initiative at the Univerita Ca Foscari di Venezia Venice}, year = {2003}, abstract = {Components and component-based technologies (componentware) are well-known and widely used in software development. There is a large amount of work and research in componentware. The number of available componentware approaches increases steadily and it is quite difficult to keep track of current trends in this area. In this paper, we survey the current state of the art in componentware, introduce and compare several well-known componentware approaches and classify them according to outstanding characteristics. We discuss a list of open issues in resarch and practical use of componentware and offer some proposals for further development. In our practical considerations we focus on embedded systems and business information systems because most of our partners in industry work in one of these two domains. We hope to start a broader discussion on componentware and to get a common understanding, which open issues are most important in research and industry (as a research agenda).}, language = {en} } @misc{Beneken2015, author = {Beneken, Gerd}, title = {PHP ist nur was f{\"u}r Hackerbuden? {\"U}ber die Bedeutung von PHP im Informatikstudium",}, editor = {Software \& Support Media GmbH,}, year = {2015}, abstract = {Vortrag zum Thema PHP im Informatikstudium}, language = {de} } @misc{Beneken2015, author = {Beneken, Gerd}, title = {Fail Better: Erfahrungen aus 12 Jahren Requirements Engineering in studentischen Projekten"}, editor = {Gesellschaft f{\"u}r Informatik,}, year = {2015}, abstract = {Vortrag zum Thema Requirements Engineering in studentischen Projekten}, language = {de} } @misc{Beneken2013, author = {Beneken, Gerd}, title = {Studienziel: Software Ingenieur(in), Studentische Projekte mit KMU}, editor = {BICCnet,}, year = {2013}, abstract = {Agenda: Studienziel Software-Ingenieur(in) � Projekte im Rahmen des Informatik-Studiums � Projektbeispiele -IT Partner in Forschungsprojekten Labor f{\"u}r Software-Technik -IT Partner in Forschungsprojekten -Einzelanfertigungen f{\"u}r genau einen Kunden -Unterst{\"u}tzung von Startups / Testen von Gesch{\"a}ftsideen -Projekte mit kleinen und mittleren Unternehmen � Zusammenarbeit mit FH: N{\"a}chste Schritte}, language = {de} } @inproceedings{WenningerSchmidtGoeller2017, author = {Wenninger, Marc and Schmidt, Jochen and Goeller, Toni}, title = {Appliance Usage Prediction for the Smart Home with an Application to Energy Demand Side Management - And Why Accuracy is not a Good Performance Metric for this Problem.}, series = {6th International Conference on Smart Cities and Green ICT Systems (SMARTGREENS)}, booktitle = {6th International Conference on Smart Cities and Green ICT Systems (SMARTGREENS)}, year = {2017}, abstract = {Shifting energy peak load is a subject that plays a huge role in the currently changing energy market, where renewable energy sources no longer produce the exact amount of energy demanded. Matching demand to supply requires behavior Changes on the customerside, which can be achieved by incentives suchas Real-Time-Pricing (RTP). Various studies show that such incentives cannot be utilized without a complexity reduction, e.g., by smart home automation systems that inform the customer about possible savings or automatically schedule appliances to off-peak load phases. We propose a probabilistic appliance usage prediction based on historical energy data that can be used to identify the times of day where an appliance will be used and therefore make load shift recommendations that suite the customer's usage profile. A huge issue is how to provide a valid performance evaluation for this particular problem. We will argue why the commonly used accuracy metric is not suitable, and suggest to use other metrics like the area under the Receiver Operating Characteristic (ROC) curve, Matthews Correlation Coefficient (MCC) or F1-Score instead.}, language = {en} } @phdthesis{Beneken2008, author = {Beneken, Gerd}, title = {Logische Architekturen: Eine Theorie der Strukturen und ihre Anwendung in Dokumentation und Projektmanagement }, school = {Technische Hochschule Rosenheim}, year = {2008}, abstract = {Software-Architektur und Projektmanagement sind Mittel, um große Software-Entwicklungsprojekte beherrschbar zu machen. Die Verbindung zwischen beiden Disziplinen wird in dieser Arbeit mithilfe einer Architekturtheorie hergestellt: Ein Verfahren wird vorgeschlagen, mit dem die Beschreibung der logischen Architektur und die Projektplanung iterativ abgeglichen und verbessert werden k{\"o}nnen. Verfahren zur architekturbasierten Optimierung der Planung werden daraus entwickelt. Die Dokumentation von Architekturen mithilfe von Architektursichten ist der zweite Schwerpunkt. Mathematisch fundierte Verfahren zur Erzeugung von Sichten werden mithilfe einer Architekturtheorie definiert. Die Verfahren erzeugen etwa Architektursichten, die Projektmanagement und die Kommunikation innerhalb des Projektes mithilfe von Planungsinformationen unterst{\"u}tzen. Ein prototypisches Werkzeug demonstriert Anwendbarkeit der Theorie und der vorgeschlagenen Verfahren}, language = {de} } @book{KuhrmannBeneken2006, author = {Kuhrmann, Marco and Beneken, Gerd}, title = {Windows® Communication Foundation: Konzepte - Programmierung - Migration}, publisher = {Spektrum Akademischer Verlag}, address = {Heidelberg}, publisher = {Technische Hochschule Rosenheim}, year = {2006}, abstract = {Eines der ersten deutschsprachigen B{\"u}cher zum Thema! Marco Kuhrmann / Gerd Beneken Windows® Communication Foundation Konzepte - Programmierung - Migration (copy) Die Windows Communication Foundation ist als Kommunikationsframework Bestandteil von .NET 3.0. Sie stellt die Grundlage f{\"u}r Service-orientierte, Web Service-basierte, verteilte Anwendungen unter Microsoft Windows dar. Dieses Buch gibt Ihnen einen umfassenden {\"U}berblick {\"u}ber die neue Plattform. Es f{\"u}hrt grundlegende Konzepte ein und stellt einen kompakten Leitfaden f{\"u}r die Softwareentwicklung auf Basis der Windows Communication Foundation dar. Anhand praktischer Beispiele werden Sie durch die Themen Services, Messaging usw. bis hin zu Fragen der Migration gef{\"u}hrt.}, language = {de} } @book{ZimmermannBeneken2000, author = {Zimmermann, J. and Beneken, Gerd}, title = {Verteilte Komponenten und Datenbankanbindung . Mehrstufige Architekturen mit SQLJ und Enterprise JavaBeansTM 2.0 (Allgemein: Datenbanken)}, publisher = {Addison-Wesley}, address = {M{\"u}nchen}, publisher = {Technische Hochschule Rosenheim}, year = {2000}, abstract = {Mehrstufige Architekturen mit SQLJ und Enterprise JavaBeans Datenbankanbindung und Erstellung von Komponenten sind ein essentieller Bestandteil von Java-Anwendungen. Bei Java-Schnittstellen r{\"u}ckt der neue ANSI-Standard SQLJ f{\"u}r relationale und objektrelationale Datenbanken immer mehr in den Blickpunkt. Bei mehrstufigen Architekturen ist dar{\"u}ber hinaus die Komponentenbildung unabdingbar, und dabei entwickelt sich EJB zu einem De-facto-Standard. Nach einer grundlegenden Einf{\"u}hrung geht es im zweiten Teil des Buches um Java-Schnittstellen zu Datenbanken: JDBC, ODMG und SQLJ8. Wie EJB-Komponenten erstellt werden und auf Java-Datenbanken zugreifen, wird im dritten Teil beschrieben.}, language = {de} } @incollection{Beneken2006, author = {Beneken, Gerd}, title = {Referenzarchitekturen}, series = {Handbuch der Software-Architektur}, booktitle = {Handbuch der Software-Architektur}, publisher = {dpunkt}, address = {Heidelberg}, publisher = {Technische Hochschule Rosenheim}, year = {2006}, abstract = {Die Architektur eines Software-Systems ist im Wesentlichen die Beschreibung des Systems anhand einzelner Beziehungen, die zwischen diesen Bausteinen bestehen. Die Wahl einer bestimmten Architektur ist eine grundlegende Entscheidung im Entwicklungsprozess und hat großen Einfluss auf die Qualit{\"a}t des sp{\"a}teren Systems. In diesem Handbuch wird erstmalig ein fundierter Einstieg und {\"U}berblick {\"u}ber den Stand der Technik und zukunftsweisende Entwicklungen im Bereich der Software-Architekturen gegeben. Ausgehend von der Rolle des Software-Architekten werden die Konstruktion und Evolution sowie Migration von Software-Architekturen systematisch aufbereitet. Als Modellierungssprache wird {\"u}berwiegend die Unified Modeling Language (UML) verwendet. Um ein umfassendes Verst{\"a}ndnis f{\"u}r die Bedeutung von Architekturbeschreibungen zu erhalten, werden auch dieThemen Management, Bewertung und Wiederverwendung von Software-Architekturen behandelt. Ebenso wird auf neuere Konzepte wie Model-Driven Architecture (MDA), Software-Produktlinien, Reverse Engineering sowie Performance- und Sicherheitsaspekte eingegangen. Dabei werden die Konzepte beispielhaft illustriert. Im Anhang befinden sich ein Kapitel {\"u}ber formale Grundlagen der Architekturmodellierung, eine {\"U}bersicht {\"u}ber Architekturbeschreibungssprachen sowie ein Glossar. Das Buch ist ein Gemeinschaftswerk der Mitglieder des Arbeitskreises Software-Architektur der Gesellschaft f{\"u}r Informatik}, language = {de} } @incollection{SeifertBeneken2005, author = {Seifert, T. and Beneken, Gerd}, title = {Evolution and Maintenance of MDA Applications}, series = {Model-Driven Software Development}, booktitle = {Model-Driven Software Development}, editor = {Beydeda, S. and Book, M. and Gruhn, V.}, publisher = {Springer}, address = {Berlin}, publisher = {Technische Hochschule Rosenheim}, year = {2005}, abstract = {Abstraction is the most basic principle of software engineering. Abstractions are provided by models. Modeling and model transformation constitute the core of model-driven development. Models can be refined and finally be transformed into a technical implementation, i.e., a software system. The aim of this book is to give an overview of the state of the art in model-driven software development. Achievements are considered from a conceptual point of view in the first part, while the second part describes technical advances and infrastructures. Finally, the third part summarizes experiences gained in actual projects employing model-driven development. Beydeda, Book and Gruhn put together the results from leading researchers in this area, both from industry and academia. The result is a collection of papers which gives both researchers and graduate students a comprehensive overview of current research issues and industrial forefront practice, as promoted by OMG's MDA initiative.}, language = {en} } @misc{Beneken2016, author = {Beneken, Gerd}, title = {http://www.sigs-datacom.de/fachzeitschriften/agile-sw-entwicklung-und-architektur-poster-2016.html}, editor = {Sigs- Datacom Verlag,}, year = {2016}, abstract = {Fachposter zur agilen Softwareentwicklung und -Architektur}, language = {de} } @misc{Beneken2015, author = {Beneken, Gerd}, title = {Agiles Projektmanagement}, editor = {Sigs- Datacom Verlag,}, year = {2015}, abstract = {Fachposter zum Thema Agiles Projektmanagement}, language = {de} } @misc{Beneken2014, author = {Beneken, Gerd}, title = {Agiles Requirements Engineering}, editor = {Sigs- Datacom Verlag,}, year = {2014}, abstract = {Fachposter zum Thema Agiles Requirements Engineering}, language = {de} } @article{BenekenDeisenboeck2004, author = {Beneken, Gerd and Deisenb{\"o}ck, F.}, title = {Java Server Faces}, series = {JavaSpektrum}, journal = {JavaSpektrum}, number = {04/2004}, year = {2004}, language = {en} } @article{BenekenSchamper2002, author = {Beneken, Gerd and Schamper, M.}, title = {Komponenten in J2EE-Patterns}, series = {JavaSpektrum}, journal = {JavaSpektrum}, number = {02/2002}, year = {2002}, language = {de} } @book{Petkovic2016, author = {Petkovic, Dusan}, title = {6. Auflage: Microsoft SQL Server 2016: A Beginner's Guide}, edition = {6}, publisher = {McGraw- Hill Osborne Media}, address = {Columbus, Ohio}, isbn = {978-1-25-964179-4}, publisher = {Technische Hochschule Rosenheim}, year = {2016}, abstract = {Get up and running on Microsoft SQL Server 2016 in no time with help from this thoroughly revised, practical resource. The book offers thorough coverage of SQL management and development and features full details on the newest business intelligence, reporting, and security features. Filled with new real-world examples and hands-on exercises, Microsoft SQL Server 2016: A Beginner's Guide, Sixth Edition, starts by explaining fundamental relational database system concepts. From there, you will learn how to write Transact-SQL statements, execute simple and complex database queries, handle system administration and security, and use the powerful analysis and BI tools. XML, spatial data, and full-text search are also covered in this step-by-step tutorial. · Revised from the ground up to cover the latest version of SQL Server · Ideal both as a self-study guide and a classroom textbook · Written by a prominent professor and best-selling author}, language = {en} } @book{Petkovic2012, author = {Petkovic, Dusan}, title = {5. Auflage- Microsoft SQL Server 2012 A Beginner's Guide}, publisher = {McGraw- Hill Osborne Media}, address = {Columbus, Ohio}, isbn = {978-0-07-176160-4}, publisher = {Technische Hochschule Rosenheim}, year = {2012}, abstract = {Get Started on Microsoft SQL Server 2012 in No TimeLearn to use all of the powerful features available in SQL Server 2012 quickly and easily. Microsoft SQL Server 2012: A Beginner's Guide explains the fundamentals of each topic alongside examples and tutorials that walk you through real-world database tasks. Install SQL Server 2012, construct high-performance databases, use powerful Transact-SQL statements, create stored procedures and triggers, and execute simple and complex database queries. Performance tuning, Database Engine security, Business Intelligence, and XML are also covered. Set up, configure, and maintain SQL Server 20012 Build and manage database objects using Transact-SQL statements Create stored procedures and user-defined functionsOptimize database performance, availability, and reliabilityImplement solid security using authentication, encryption, and authorization Automate tasks using SQL Server AgentCreate reliable data backups and perform flawless system restoresUse all-new SQL Server 2012 Business Intelligence, development, and administration toolsLearn in detail the SQL Server XML technology (SQLXML)}, language = {en} } @book{Petkovic2008, author = {Petkovic, Dusan}, title = {4. Auflage- Microsoft SQL Server 2008, A Beginner's Guide}, edition = {4. Auflage}, publisher = {McGraw- Hill Osborne Media}, address = {Columbus, Ohio}, isbn = {978-0-07-154638-6}, publisher = {Technische Hochschule Rosenheim}, year = {2008}, abstract = {Get Started on Microsoft SQL Server 2008 in No TimeLearn to use all of the powerful features available in SQL Server 2008 quickly and easily. Microsoft SQL Server 2008: A Beginner's Guide explains the fundamentals of each topic alongside examples and tutorials that walk you through real-world database tasks. Install SQL Server 2008, construct high-performance databases, use powerful Transact-SQL statements, create stored procedures and triggers, and execute simple and complex database queries. Performance tuning, Database Engine security, Business Intelligence, and XML are also covered. Set up, configure, and maintain SQL Server 2008 Build and manage database objects using Transact-SQL statements Create stored procedures and user-defined functionsOptimize database performance, availability, and reliability Implement solid security using authentication, encryption, and authorization Automate tasks using SQL Server Agent Create reliable data backups and perform flawless system restores Use all-new SQL Server 2008 Business Intelligence, development, and administration toolsLearn in detail the SQL Server XML technology (SQLXML)}, language = {en} } @book{Petkovic2005, author = {Petkovic, Dusan}, title = {3. Auflage - Microsoft SQL Server 2005: A Beginner's Guide}, publisher = {McGraw- Hill Osborne Media}, address = {Columbus, Ohio}, isbn = {0-07-226093-9}, publisher = {Technische Hochschule Rosenheim}, year = {2005}, abstract = {Deploy and manage SQL Server 2005 with easeLearn to use all the powerful features available in SQL Server 2005 from this straightforward, hands-on guide. Set up SQL Server 2005, automate system administration tasks, execute simple and complex database queries, and use the robust analysis, business intelligence, and reporting tools. Troubleshooting, data partitioning, replication, and query optimization are also covered. With SQL Server 2005: A Beginner's Guide, you'll be able to set up a secure, reliable, and productive data management platform in no time. Essential Skills for Database Professionals - Install and customize SQL Server 2005 - Create, alter, and remove database objects with Transact-SQL statements - Use SQL Server as a native XML database system - Tune your database system for optimal performance - Use the new SQL Server Management Studio tool for executing and analyzing ad hoc queries - Retrieve data from more than one source using join operations and SELECT statements - Secure your database using two different authentication modes--Windows and mixed - Restore databases using transaction logs and backup and recovery methods - Streamline system administration tasks using the SQL Server Agent service tool - Analyze and manage information stored in a data warehouse with Microsoft Analysis Services}, language = {en} } @book{Petkovic2000, author = {Petkovic, Dusan}, title = {2. Auflage- SQL Server 2000: A Beginner's Guide}, publisher = {McGraw- Hill Osborne Media}, address = {Columbus, Ohio}, isbn = {978-0072125870}, publisher = {Technische Hochschule Rosenheim}, year = {2000}, abstract = {Your one-stop solution for getting up and running with SQL Server 2000 Develop and deploy large-scale applications with SQL Server 2000. In this book, database expert Dusan Petkovic explains how to use all the features of this powerful, scaleable relational database management system. You'll learn to configure SQL Server 2000, use T-SQL, execute efficient database queries, and enable secure transactions. Troubleshooting, data warehousing, and optimization are also covered. You'll find complete details on Microsoft Analysis Services, managing multiple servers, maximizing uptime, and performance tuning. With SQL Server 2000: A Beginner's Guide, your mission-critical database applications will be up-and-running in no time! Learn to: Setup, manage, and customize SQL Server 2000 Administer multiple instances of SQL Server 2000 using the SQL Server Enterprise Manager Perform simple and complex database queries Tune the performance of your SELECT statements Use SQL extensions, stored procedures, transactions, views, and triggers Implement the SQL Server 2000 security model Find and fix database problems by capturing and replaying server activity Import, export, and transform data types using DTS Construct data warehouses to collect, organize, and distribute information efficiently}, language = {en} } @book{Petkovic1999, author = {Petkovic, Dusan}, title = {Erstauflage- Microsoft SQL Server 7: A Beginner's Guide}, edition = {1}, publisher = {McGraw- Hill Osborne Media}, address = {Columbus, Ohio}, isbn = {0-07-211891-1}, publisher = {Technische Hochschule Rosenheim}, year = {1999}, abstract = {Create, query, and manage high-performance SQL Server 7 databases with the hot new release of this scalable database management system. SQL Server 7: A Beginner's Guide explains enterprise database fundamentals and shows you how to take advantage of the new features of SQL Server 7, such as improved space management, new data transformation services, and data warehousing. From installation to query optimization to security to data warehousing, this hands-on guide provides everything you need to know to get up and running smoothly on SQL Server 7.}, language = {en} } @inproceedings{RiedhammerBockletOrozcoArroyaveetal.2014, author = {Riedhammer, Korbinian and Bocklet, Tobias and Orozco-Arroyave, Juan Rafael and N{\"o}th, Elmar}, title = {Semi-Automatic Calibration for Dereverberation by Spectral Subtraction for Continuous Speech Recognition}, series = {ITG Symposium on Speech Communication 2014, Erlangen.}, booktitle = {ITG Symposium on Speech Communication 2014, Erlangen.}, publisher = {VDE VERLAG GMBH}, year = {2014}, abstract = {In this article, we describe a semi-automatic calibration algorithm for dereverberation by spectral subtraction. We verify the method by a comparison to a manual calibration derived from measured room impulse responses (RIR). We conduct extensive experiments to understand the effect of all involved parameters and to verify values suggested in the literature. The experiments are performed on a text read by 31 speakers and recorded by a headset and three far-field microphones. Results are measured in terms of automatic speech recognition (ASR) performance using a 1-gram model to emphasize acoustic recognition performance. To accommodate for the acoustic change by dereverberation we apply supervised MAP adaptation to the hidden Markov model output probabilities. The combination of dereverberation and adaptation yields a relative improvement of about 35\% in terms of word error rate (WER) compared to the original signal.}, language = {en} } @inproceedings{GhahremaniBabaAliPoveyetal.2014, author = {Ghahremani, Pegah and BabaAli, Bagher and Povey, Daniel and Riedhammer, Korbinian and Trmal, Jan and Khudanpur, Sanjeev}, title = {A Pitch Extraction Algorithm Tuned for Automatic Speech Recognition}, series = {2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 2014.}, booktitle = {2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 2014.}, publisher = {IEEE}, year = {2014}, abstract = {In this paper we present an algorithm that produces pitch and probability-of-voicing estimates for use as features in automatic speech recognition systems. These features give large performance improvements on tonal languages for ASR systems, and even substantial improvements for non-tonal languages. Our method, which we are calling the Kaldi pitch tracker (because we are adding it to the Kaldi ASR toolkit), is a highly modified version of the getf0 (RAPT) algorithm. Unlike the original getf0 we do not make a hard decision whether any given frame is voiced or unvoiced; instead, we assign a pitch even to unvoiced frames while constraining the pitch trajectory to be continuous. Our algorithm also produces a quantity that can be used as a probability of voicing measure; it is based on the normalized autocorrelation measure that our pitch extractor uses. We present results on data from various languages in the BABEL project, and show a large improvement over systems without tonal features and systems where pitch and POV information was obtained from SAcC or getf0.}, language = {en} } @inproceedings{BockletMaierRiedhammeretal.2014, author = {Bocklet, Tobias and Maier, Andreas and Riedhammer, Korbinian and Eysholdt, Ulrich and N{\"o}th, Elmar}, title = {Erlangen-CLP: A Large Annotated Corpus of Speech from Children with Cleft Lip and Palate.}, series = {Language Resources and Evaluation Conference (LREC), Reykjavik, Iceland, May 2014.}, booktitle = {Language Resources and Evaluation Conference (LREC), Reykjavik, Iceland, May 2014.}, year = {2014}, abstract = {In this paper we describe Erlangen-CLP, a large speech database of children with Cleft Lip and Palate. More than 800 German children with CLP (most of them between 4 and 18 years old) and 380 age matched control speakers spoke the semi-standardized PLAKSS test that consists of words with all German phonemes in different positions. So far 250 CLP speakers were manually transcribed, 120 of these were analyzed by a speech therapist and 27 of them by four additional therapists. The tharapists marked 6 different processes/criteria like pharyngeal backing and hypernasality which typically occur in speech of people with CLP. We present detailed statistics about the the marked processes and the inter-rater agreement.}, language = {en} } @inproceedings{WegmannFariaJaninetal.2013, author = {Wegmann, Steven and Faria, Arlo and Janin, Adam and Riedhammer, Korbinian and Morgan, Nelson}, title = {The Tao of ATWV: Probing the mysteries of keyword search performance}, series = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Olomouc, Czech Republic, Dezember 2013.}, booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Olomouc, Czech Republic, Dezember 2013.}, year = {2013}, abstract = {In this paper we apply diagnostic analysis to gain a deeper understanding of the performance of the the keyword search system that we have developed for conversational telephone speech in the IARPA Babel program. We summarize the Babel task, its primary performance metric, "actual term weighted value" (ATWV), and our recognition and keyword search systems. Our analysis uses two new oracle ATWV measures, a bootstrap-based ATWV confidence interval, and includes a study of the underpinnings of the large ATWV gains due to system combination. This analysis quantifies the potential ATWV gains from improving the number of true hits and the overall quality of the detection scores in our system's posting lists. It also shows that system combination improves our systems' ATWV via a small increase in the number of true hits in the posting lists.}, language = {en} } @inproceedings{RiedhammerGroppBockletetal.2013, author = {Riedhammer, Korbinian and Gropp, Martin and Bocklet, Tobias and H{\"o}nig, Florian and N{\"o}th, Elmar and Steidl, Stefan}, title = {LMELectures: A Multimedia Corpus of Academic Spoken English}, series = {First Workshop on Speech, Language and Audio in Multimedia (SLAM 2013), Marseille, France, August 2013, ISCA Archive.}, booktitle = {First Workshop on Speech, Language and Audio in Multimedia (SLAM 2013), Marseille, France, August 2013, ISCA Archive.}, pages = {102 -- 107}, year = {2013}, abstract = {This paper describes the acquisition, transcription and annotation of a multi-media corpus of academic spoken English, the LMELectures. It consists of two lecture se-ries that were read in the summer term 2009 at the com-puter science department of the University of Erlangen-Nuremberg, covering topics in pattern analysis, machine learning and interventional medical image processing. In total, about 40 hours of high-definition audio and video of a single speaker was acquired in a constant recording en-vironment. In addition to the recordings, the presentation slides are available in machine readable (PDF) format. The manual annotations include a suggested segmenta-tion into speech turns and a complete manual transcrip-tion that was done using BLITZSCRIBE2, a new tool for the rapid transcription. For one lecture series, the lecturer assigned key words to each recordings; one recording of that series was further annotated with a list of ranked key phrases by five human annotators each. The corpus is available for non-commercial purpose upon request.}, language = {en} } @inproceedings{RiedhammerHaiDoHieronymus2013, author = {Riedhammer, Korbinian and Hai Do, Van and Hieronymus, James}, title = {A Study on LVCSR and Keyword Search for Tagalog}, series = {INTERSPEECH 2013, 14th Annual Conference of the International Speech Communication Association (ISCA), Lyon, France, August 2013.}, booktitle = {INTERSPEECH 2013, 14th Annual Conference of the International Speech Communication Association (ISCA), Lyon, France, August 2013.}, year = {2013}, abstract = {We describe a state-of-the-art large vocabulary continuous speech recognition (LVCSR) and keyword search (KWS) system trained on roughly 70 hours of conversational telephone speech. Using the Kaldi speech recognition toolkit, we investigate several aspects: for the acoustic front-end, we analyze the use of mel-frequency cepstral coefficients (MFCC), pitch and probability-of-voicing (PoV), and deep neural network (DNN) bottleneck (BN) features, as well as their feature-level combination ("tandem"). For the acousticphonetic decision tree, we explore different hidden Markov model (HMM) topologies for the glottalization phoneme /?/ to model its typically short duration. For the acoustic model, we compare regular continuous HMM with a sort of multi-codebook subspace Gaussian mixture model (SGMM) that lead to an overall best word error rate (WER) of 58.7\% and 56.3\%, respectively. The KWS is implemented as a word lattice search, and is augmented by a syllable lattice back-up search to capture out-of-vocabulary keywords as well as misrecognized lexical surface forms due to ambiguous prefix and hyphenation rules.}, language = {en} } @inproceedings{BockletRiedhammerEysholdtetal.2013, author = {Bocklet, Tobias and Riedhammer, Korbinian and Eysholdt, Ulrich and N{\"o}th, Elmar}, title = {Automatic Phoneme Analysis in Children with Cleft Lip and Palate}, series = {2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada, May 2013.}, booktitle = {2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada, May 2013.}, publisher = {IEEE}, pages = {7572 -- 7576}, year = {2013}, abstract = {Cleft Lip and Palate (CLP) is among the most frequent congenital abnormalities. The impaired facial development affects the articulation, with different phonemes being impacted inhomogeneously among different patients. This work focuses on automatic phoneme analysis of children with CLP for a detailed diagnosis and therapy control. In clinical routine, the state-of-the-art evaluation is based on perceptual evaluations. Perceptual ratings act as ground-truth throughout this work, with the goal to build an automatic system that is as reliable as humans. We propose two different automatic systems focusing on modeling the articulatory space of a speaker: one system models a speaker by a GMM, the other system employs a speech recognition system and estimates fMLLR matrices for each speaker. SVR is then used to predict the perceptual ratings. We show that the fMLLR-based system is able to achieve automatic phoneme evaluation results that are in the same range as perceptual inter-rater-agreements.}, language = {en} } @inproceedings{RiedhammerGroppNoeth2012, author = {Riedhammer, Korbinian and Gropp, Martin and N{\"o}th, Elmar}, title = {The FAU Video Lecture Browser System}, series = {2012 IEEE Spoken Language Technology Workshop (SLT), Miami, FL, USA, December 2012.}, booktitle = {2012 IEEE Spoken Language Technology Workshop (SLT), Miami, FL, USA, December 2012.}, publisher = {IEEE}, pages = {392 -- 397}, year = {2012}, abstract = {A growing number of universities and other educational institutions provide recordings of lectures and seminars as an additional resource to the students. In contrast to educational films that are scripted, directed and often shot by film professionals, these plain recordings are typically not post-processed in an editorial sense. Thus, the videos often contain longer periods of inactivity or silence, unnecessary repetitions, or corrections of prior mistakes. This paper describes the FAU Video Lecture Browser system, a web-based platform for the interactive assessment of video lectures, that helps to close the gap between a plain recording and a useful e-learning resource by displaying automatically extracted and ranked key phrases on an augmented time line based on stream graphs. In a pilot study, users of the interface were able to complete a topic localization task about 29 \% faster than users provided with the video only while achieving about the same accuracy. The user interactions can be logged on the server to collect data to evaluate the quality of the phrases and rankings, and to train systems that produce customized phrase rankings.}, language = {en} } @inproceedings{HoenigBockletRiedhammeretal.2012, author = {H{\"o}nig, Florian and Bocklet, Tobias and Riedhammer, Korbinian and Batliner, Anton and N{\"o}th, Elmar}, title = {The Automatic Assessment of Non-native Prosody: Combining Classical Prosodic Analysis with Acoustic Modelling}, series = {INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association (ISCA), Portland, OR, USA, September 2012.}, booktitle = {INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association (ISCA), Portland, OR, USA, September 2012.}, year = {2012}, abstract = {In earlier studies, we assessed the degree of non-nativeness employing prosodic information. In this paper, we combine prosodic information with (1) features derived from a Gaussian Mixture Model used as Universal Background Model (GMM-UBM), a powerful approach used in speaker identification, and (2) openSMILE, a standard open-source toolkit for extracting acoustic features. We evaluate our approach with English speech from 94 non-native speakers. GMM-UBM or openSMILE modelling alone yields lower performance than our prosodic feature vector; however, adding information from the GMM-UBM modelling or openSMILE by late fusion improves results.}, language = {en} } @inproceedings{RiedhammerRingNoethetal.2012, author = {Riedhammer, Korbinian and Ring, Martin and N{\"o}th, Elmar and Kolb, Daniel}, title = {A Software Kit for Automatic Voice Descrambling}, series = {2012 IEEE International Conference on Communications (ICC); IEEE International Workshop on Security and Forensics in Communication Systems (SFCS).}, booktitle = {2012 IEEE International Conference on Communications (ICC); IEEE International Workshop on Security and Forensics in Communication Systems (SFCS).}, pages = {8349 -- 8353}, year = {2012}, abstract = {Voice scrambling is widely used to add privacy to the radio communication of various authorities - but is also used by criminals to evade prosecution. In this article, we consider various analog voice scrambling techniques such as fixed frequency inversion, splitband inversion and rolling code scramblers. We explain how to break them using automatically extracted measures and scoring algorithms, and evaluate the proposed system using simulated data. While the simple inversion can be easily broken, the more advanced techniques require additional work prior to unsupervised automatization; the presented user interface allows the user to refine the automatic results to obtain a high quality solution.}, language = {en} } @inproceedings{RiedhammerBockletGoshaletal.2012, author = {Riedhammer, Korbinian and Bocklet, Tobias and Goshal, Arnab and Povey, Daniel}, title = {Revisiting Semi-Continuous Hidden Markov Models}, series = {2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, March 2012.}, booktitle = {2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, March 2012.}, publisher = {IEEE}, pages = {4721 -- 4724}, year = {2012}, abstract = {In the past decade, semi-continuous hidden Markov models (SCHMMs) have not attracted much attention in the speech recognition community. Growing amounts of training data and increasing sophistication of model estimation led to the impression that continuous HMMs are the best choice of acoustic model. However, recent work on recognition of under-resourced languages faces the same old problem of estimating a large number of parameters from limited amounts of transcribed speech. This has led to a renewed interest in methods of reducing the number of parameters while maintaining or extending the modeling capabilities of continuous models. In this work, we compare classic and multiple-codebook semi-continuous models using diagonal and full covariance matrices with continuous HMMs and subspace Gaussian mixture models. Experiments on the RM and WSJ corpora show that while a classical semicontinuous system does not perform as well as a continuous one, multiple-codebook semi-continuous systems can perform better, particular when using full-covariance Gaussians.}, language = {en} } @inproceedings{PoveyHannemannBoulianneetal.2012, author = {Povey, Daniel and Hannemann, Mirko and Boulianne, Gilles and Burget, Luk{\´a}š and Ghoshal, Arnab and Janda, Miloš and Karafi{\´a}t, Martin and Kombrink, Stefan and Motl{\´i}ček, Petr and Qian, Yanmin and Riedhammer, Korbinian and Vesel{\´y}, Karel and Thang Vu, Ngoc}, title = {Generating Exact Lattices in the WFST Framework}, series = {2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, May 2012.}, booktitle = {2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, May 2012.}, pages = {4213 -- 4216}, year = {2012}, abstract = {We describe a lattice generation method that is exact, i.e. it satisfies all the natural properties we would want from a lattice of alternative transcriptions of an utterance. This method does not introduce substantial overhead above one-best decoding. Our method is most directly applicable when using WFST decoders where the WFST is "fully expanded", i.e. where the arcs correspond to HMM transitions. It outputs lattices that include HMM-state-level alignments as well as word labels. The general idea is to create a state-level lattice during decoding, and to do a special form of determinization that retains only the best-scoring path for each word sequence. This special determinization algorithm is a solution to the following problem: Given a WFST A, compute a WFST B that, for each input-symbol-sequence of A, contains just the lowest-cost path through A.}, language = {en} } @inproceedings{RiedhammerGroppNoeth2011, author = {Riedhammer, Korbinian and Gropp, Martin and N{\"o}th, Elmar}, title = {A Novel Lecture Browser Using Key Phrases and Stream Graphs}, series = {Lehrstuhl f{\"u}r Mustererkennung, Universit{\"a}t Erlangen-N{\"u}rnberg}, booktitle = {Lehrstuhl f{\"u}r Mustererkennung, Universit{\"a}t Erlangen-N{\"u}rnberg}, year = {2011}, abstract = {We present a novel lecture browser that utilizes ranked key phrases displayed on a stream graph to overcome the shortcomings of traditional extractive (query-based) summaries. The system extracts key phrases from the ASR transcripts, performs an unsupervised ranking, and displays an initial number of phrases on the stream graph. This graph gives an intuition of when which key phrase is spoken, and how dominant it is throughout the lecture. The user can select the phrases to be displayed and furthermore adjust the ranking of the all phrases. All user interactions are logged to a server to improve the ranking algorithms and provide user specific rankings.}, language = {en} } @inproceedings{GroppNoethRiedhammer2011, author = {Gropp, Martin and N{\"o}th, Elmar and Riedhammer, Korbinian}, title = {A Novel Lecture Browsing System Using Ranked Key Phrases and StreamGraphs}, series = {14th International Conference on Text, Speech and Dialogue (TSD), September 2011, Pilsen, Czech Republic.}, booktitle = {14th International Conference on Text, Speech and Dialogue (TSD), September 2011, Pilsen, Czech Republic.}, pages = {17 -- 24}, year = {2011}, abstract = {A growing number of universities offer recordings of lectures, seminars and talks in an online e-learning portal. However, the user is often not interested in the entire recording, but is looking for parts covering a certain topic. Usually, the user has to either watch the whole video or "zap" through the lecture and risk missing important details. We present an integrated web-based platform to help users find relevant sections within recorded lecture videos by providing them with a ranked list of key phrases. For a user-defined subset of these, a StreamGraph visualizes when important key phrases occur and how prominent they are at the given time. To come up with the best key phrase rankings, we evaluate three different key phrase ranking methods using lectures of different topics by comparing automatic with human rankings, and show that human and automatic rankings yield similar scores using Normalized Discounted Cumulative Gain (NDCG).}, language = {en} } @inproceedings{SteidlRiedhammerBockletetal.2011, author = {Steidl, Stefan and Riedhammer, Korbinian and Bocklet, Tobias and H{\"o}nig, Florian and N{\"o}th, Elmar}, title = {Java Visual Speech Components for Rapid Application Development of GUI based Speech Processing Applications}, series = {INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 2011.}, booktitle = {INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 2011.}, pages = {3257 -- 3260}, year = {2011}, abstract = {In this paper, we describe a new Java framework for an easy and efficient way of developing new GUI based speech processing applications. Standard components are provided to display the speech signal, the power plot, and the spectrogram. Furthermore, a component to create a new transcription and to display and manipulate an existing transcription is provided, as well as a component to display and manually correct external pitch values. These Swing components can be easily embedded into own Java programs. They can be synchronized to display the same region of the speech file. The object-oriented design provides base classes for rapid development of own components.}, language = {en} } @inproceedings{BockletRiedhammerNoeth2011, author = {Bocklet, Tobias and Riedhammer, Korbinian and N{\"o}th, Elmar}, title = {Drink and Speak: On the automatic classification of alcohol intoxination by acoustic, prosodic and text-based features}, series = {INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 2011.}, booktitle = {INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 2011.}, pages = {3213 -- 3216}, year = {2011}, abstract = {This paper focuses on the automatic detection of a person's blood level alcohol based on automatic speech processing approaches. We compare 5 different feature types with different ways of modeling. Experiments are based on the ALC corpus of IS2011 Speaker State Challenge. The classification task is restricted to the detection of a blood alcohol level above 0.5 per mille. Three feature sets are based on spectral observations: MFCCs, PLPs, TRAPS. These are modeled by GMMs. Classification is either done by a Gaussian classifier or by SVMs. In the later case classification is based on GMM-based supervectors, i.e. concatenation of GMM mean vectors. A prosodic system extracts a 292-dimensional feature vector based on a voiced-unvoiced decision. A transcription-based system makes use of text transcriptions related to phoneme durations and textual structure. We compare the stand-alone performances of these systems and combine them on score level by logistic regression. The best stand-alone performance is the transcriptionbased system which outperforms the baseline by 4.8\% on the development set. A Combination on score level gave a huge boost when the spectral-based systems were added (73.6\%). This is a relative improvement of 12.7\% to the baseline. On the test-set we achieved an UA of 68.6\% which is a significant improvement of 4.1\% to the baseline system.}, language = {en} } @inproceedings{RiedhammerBockletNoeth2011, author = {Riedhammer, Korbinian and Bocklet, Tobias and N{\"o}th, Elmar}, title = {Compensation of Extrinsic Variability in Speaker Verification Systems on Simulated Skype and HF Channel Data}, series = {2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, May 2011.}, booktitle = {2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, May 2011.}, pages = {4840 -- 4843}, year = {2011}, abstract = {In this work we focus on speaker verification on channels of varying quality, namely Skype and high frequency (HF) radio. In our setup, we assume to have telephone recordings of speakers for training, but recordings of different channels for testing with varying (lower) signal quality. Starting from a Gaussian mixture / support vector machine (GMM/SVM) baseline, we evaluate multi-condition training (MCT), an ideal channel classification approach (ICC), and nuisance attribute projection (NAP) to compensate for the loss of information due to the transmission. In an evaluation on Switchboard-2 data using Skype and HF channel simulators, we show that, for good signal quality, NAP improves the baseline system performance from 5\% EER to 3.33\% EER (for both Skype and HF). For strongly distorted data, MCT or, if adequate, ICC turn out to be the method of choice.}, language = {en} } @inproceedings{KiesmuellerSossallaBrindaetal.2010, author = {Kiesm{\"u}ller, Ulrich and Sossalla, Sebastian and Brinda, Torsten and Riedhammer, Korbinian}, title = {Online Identification of Learner Problem Solving Strategies Using Pattern Recognition Methods}, series = {Proceedings of the 15th Annual Conference on Innovation and Technology in Computer Science Education (ITiCSE 2010), Bilkent, Ankara, Turkey, June 2010.}, booktitle = {Proceedings of the 15th Annual Conference on Innovation and Technology in Computer Science Education (ITiCSE 2010), Bilkent, Ankara, Turkey, June 2010.}, pages = {274 -- 278}, year = {2010}, abstract = {Learning and programming environments used in computer science education give feedback to the users by system messages. These are triggered by programming errors and give only "technical" hints without regard to the learners' problem solving process. To adapt the messages not only to the factual but also to the procedural knowledge of the learners, their problem solving strategies have to be identified automatically and in process. This article describes a way to achieve this with the help of pattern recognition methods. Using data from a study with 65 learners aged 12 to 13 using a learning environment for programming, a classification system based on hidden Markov models is trained and integrated in the very same environment. We discuss findings in that data and the performance of the automatic online identification, and present first results using the developed software in class.}, language = {en} } @inproceedings{ZaehRiedhammerBockletetal.2010, author = {Z{\"a}h, Uwe and Riedhammer, Korbinian and Bocklet, Tobias and N{\"o}th, Elmar}, title = {Clap Your Hands! Calibrating Spectral Subtraction for Dereverberation}, series = {2010 IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), Dallas, TX, USA, March 2010.}, booktitle = {2010 IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), Dallas, TX, USA, March 2010.}, pages = {4226 -- 4229}, year = {2010}, abstract = {Reverberation effects as observed by room microphones severely degrade the performance of automatic speech recognition systems. We investigate the use of dereverberation by spectral subtraction as proposed by Lebart and Boucher and introduce a simple approach to estimate the required decay parameter by clapping hands. Experiments on small vocabulary continuous speech recognition task on read speech show that using the calibrated dereverberation improves WER from 73.2 to 54.7 for the best microphone. In combination with system adaptation, the WER could be reduced to 28.2, which is only a 16\% relative loss of performance comparison to using a headset instead of a room microphone.}, language = {en} } @inproceedings{SpieglRiedhammerSteidletal.2010, author = {Spiegl, Werner and Riedhammer, Korbinian and Steidl, Stefan and N{\"o}th, Elmar}, title = {FAU IISAH Corpus - A German Speech Database Consisting of Human-Machine and Human-Human Interaction Acquired by Close-Talking and Far-Distance Microphones}, series = {7th Conference on International Language Resources and Evaluation (LREC 2010), European Language Resources Association (ELRA), Valletta, Malta, May 2010.}, booktitle = {7th Conference on International Language Resources and Evaluation (LREC 2010), European Language Resources Association (ELRA), Valletta, Malta, May 2010.}, pages = {2420 -- 2423}, year = {2010}, language = {en} } @inproceedings{BockletMaierRiedhammeretal.2009, author = {Bocklet, Tobias and Maier, Andreas and Riedhammer, Korbinian and N{\"o}th, Elmar}, title = {Towards a Language-independent Intelligibility Assessment of Children with Cleft Lip and Palate}, series = {WOCCI '09 Proceedings of the 2nd Workshop on Child, Computer and Interaction (WOCCI 2009), Cambridge, Massachusetts, November 2009, Article No. 6.}, booktitle = {WOCCI '09 Proceedings of the 2nd Workshop on Child, Computer and Interaction (WOCCI 2009), Cambridge, Massachusetts, November 2009, Article No. 6.}, organization = {ACM New York, NY, USA ©2009}, pages = {2015 -- 2018}, year = {2009}, abstract = {We describe a novel evaluation system for the intelligibility assessment of children with CLP on standardized tests. The system is solely based on standard cepstral features in form of MFCCs. No other information like word alignments is used. So the system can be easily adapted to other languages. For each child one GMM is created by adaptation of a UBM to the speaker-specific MFCCs. The components of this GMM are concatenated in order to create a so-called GMM supervector. These GMM supervectors are then used as meta features for an SVR. We evaluated our language-independent system on two different datasets of children suffering from CLP. One dataset contains recordings of 35 German children, where the children named different pictograms. The other dataset contains recordings of 14 Italian speaking children, who repeated standardized sentences. On both datasets we achieved high correlations: up to 0.81 for the German dataset and 0.83 for the Italian dataset.}, language = {en} } @inproceedings{FariaRiedhammerJaninetal.2016, author = {Faria, Arlo and Riedhammer, Korbinian and Janin, Adam and Bauer, A.}, title = {REMEETING: Searchable Conversations}, series = {INTERSPEECH 2016, Annual Conference of the International Speech Communication Association (ISCA), IEEE Workshop on Spoken Language Technologies (SLT), San Francisco, USA, September 2016.}, booktitle = {INTERSPEECH 2016, Annual Conference of the International Speech Communication Association (ISCA), IEEE Workshop on Spoken Language Technologies (SLT), San Francisco, USA, September 2016.}, organization = {2016 ISCA}, year = {2016}, language = {en} } @inproceedings{FariaRiedhammer2015, author = {Faria, Arlo and Riedhammer, Korbinian}, title = {REMEETING — Get More Out Of Meetings}, series = {INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 2015.}, booktitle = {INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 2015.}, year = {2015}, abstract = {Remeeting is a tool that helps you get more out of in-person meetings. Calendar integration and a special email address allow users to email agenda items prior to a certain meeting. A discrete notification at the time of the meeting reminds the user to start the recording. During the meeting, the user focuses on the conversation, or can add notes and photos if desired. After the meeting, every participant gets notified by an automated email that lists the participants along with automatically extracted keywords, notes and photos. This stimulates collaboration, and keeps follow-up contributions at a central place: Just reply to add further notes to the meeting. The resulting meeting "document" can be shared with others and reviewed using a web app that acts as a visual index to the meeting. This makes Remeeting the perfect tool for regular group meetings, standups and interviews, where people typically track progress and follow up on. Remeeting is leveraging, promoting and contributing to open source projects including kaldi and docker.}, language = {en} } @inproceedings{FariaRiedhammer2014, author = {Faria, Arlo and Riedhammer, Korbinian}, title = {REMEETING — Get More Out of Meetings}, series = {INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, IEEE Workshop on Spoken Language Technologies (SLT), Singapore, September 2014.}, booktitle = {INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, IEEE Workshop on Spoken Language Technologies (SLT), Singapore, September 2014.}, year = {2014}, language = {en} } @inproceedings{GargFavreRiedhammeretal.2009, author = {Garg, Nikhil and Favre, Benoit and Riedhammer, Korbinian and Hakkani-T{\"u}r, Dilek}, title = {A Graph Based Method for Meeting Summarization}, series = {INTERSPEECH 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 2009.}, booktitle = {INTERSPEECH 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 2009.}, pages = {1499 -- 1502}, year = {2009}, abstract = {This paper presents an unsupervised, graph based approach for extractive summarization of meetings. Graph based methods such as TextRank have been used for sentence extraction from news articles. These methods model text as a graph with sentences as nodes and edges based on word overlap. A sentence node is then ranked according to its similarity with other nodes. The spontaneous speech in meetings leads to incomplete, informed sentences with high redundancy and calls for additional measures to extract relevant sentences. We propose an extension of the TextRank algorithm that clusters the meeting utterances and uses these clusters to construct the graph. We evaluate this method on the AM I meeting corpus and show a significant improvement over TextRank and other baseline methods.}, language = {en} } @inproceedings{GillickRiedhammerFavreetal.2009, author = {Gillick, Dan and Riedhammer, Korbinian and Favre, Benoit and Hakkani-T{\"u}r, Dilek}, title = {A Global Optimization Framework for Meeting Summarization}, series = {2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Taipei, Taiwan, April 2009.}, booktitle = {2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Taipei, Taiwan, April 2009.}, pages = {4769 -- 4772}, year = {2009}, abstract = {We introduce a model for extractive meeting summarization based on the hypothesis that utterances convey bits of information, or concepts. Using keyphrases as concepts weighted by frequency, and an integer linear program to determine the best set of utterances, that is, covering as many concepts as possible while satisfying a length constraint, we achieve ROUGE scores at least as good as a ROUGE-based oracle derived from human summaries. This brings us to a critical discussion of ROUGE and the future of extractive meeting summarization.}, language = {en} } @inproceedings{RiedhammerFavreHakkaniTuer2008, author = {Riedhammer, Korbinian and Favre, Benoit and Hakkani-T{\"u}r, Dilek}, title = {A Keyphrase Based Approach to Interactive Meeting Summarization}, series = {2008 IEEE Workshop on Spoken Language Technologies (SLT), Goa, India, December 2008.}, booktitle = {2008 IEEE Workshop on Spoken Language Technologies (SLT), Goa, India, December 2008.}, pages = {153 -- 156}, year = {2008}, abstract = {Rooted in multi-document summarization, maximum marginal relevance (MMR) is a widely used algorithm for meeting summarization (MS). A major problem in extractive MS using MMR is finding a proper query: the centroid based query which is commonly used in the absence of a manually specified query, can not significantly outperform a simple baseline system. We introduce a simple yet robust algorithm to automatically extract keyphrases (KP) from a meeting which can then be used as a query in the MMR algorithm. We show that the KP based system significantly outperforms both baseline and centroid based systems. As human refined KPs show even better summarization performance, we outline how to integrate the KP approach into a graphical user interface allowing interactive summarization to match the user's needs in terms of summary length and topic focus.}, language = {en} } @inproceedings{TurStolckeVossetal.2008, author = {Tur, Gokhan and Stolcke, Andreas and Voss, Lynn and Dowding, John and Favre, Benoit and Fernandez, Raquel and Frampton, Matthew and Frandsen, Michael and Frederickson, Clive and Graciarena, Martin and Hakkani-T{\"u}r, Dilek and Kintzing, Donald and Leveque, Kyle and Mason, Shane and Niekrasz, John and Peters, Stanley and Purver, Matthew and Riedhammer, Korbinian and Shriberg, Elizabeth and Tien, Jing and Vergyri, Dimitra and Yang, Fan}, title = {The CALO Meeting Speech Recognition and Understanding System}, series = {2008 IEEE Workshop on Spoken Language Technologies (SLT), Goa, India, December 2008.}, booktitle = {2008 IEEE Workshop on Spoken Language Technologies (SLT), Goa, India, December 2008.}, pages = {69 -- 72}, year = {2008}, abstract = {The CALO meeting assistant provides for distributed meeting capture, annotation, automatic transcription and semantic analysis of multiparty meetings, and is part of the larger CALO personal assistant system. This paper summarizes the CALO-MA architecture and its speech recognition and understanding components, which include real-time and offline speech transcription, dialog act segmentation and tagging, question-answer pair identification, action item recognition, decision extraction, and summarization.}, language = {en} } @inproceedings{RiedhammerGillickFavreetal.2008, author = {Riedhammer, Korbinian and Gillick, Dan and Favre, Benoit and Hakkani-T{\"u}r, Dilek}, title = {Packing the Meeting Summarization Knapsack}, series = {INTERSPEECH 2008, 9th Annual Conference of the International Speech Communication Association (ISCA), Brisbane, Australia, September 2008.}, booktitle = {INTERSPEECH 2008, 9th Annual Conference of the International Speech Communication Association (ISCA), Brisbane, Australia, September 2008.}, pages = {2434 -- 2437}, year = {2008}, abstract = {Despite considerable work in automatic meeting summarization over the last few years, comparing results remains difficult due to varied task conditions and evaluations. To address this issue, we present a method for determining the best possible extractive summary given an evaluation metric like ROUGE. Our oracle system is based on a knapsack-packing framework, and though NP-Hard, can be solved nearly optimally by a genetic algorithm. To frame new research results in a meaningful context, we suggest presenting our oracle results alongside two simple baselines. We show oracle and baseline results for a variety of evaluation scenarios that have recently appeared in this field.}, language = {en} } @inproceedings{RiedhammerStemmerHaderleinetal.2007, author = {Riedhammer, Korbinian and Stemmer, Georg and Haderlein, Tino and Schuster, Mario and Rosanowski, Frank and N{\"o}th, Elmar and Maier, Andreas}, title = {Towards Robust Automatic Evaluation of Pathologic Telephone Speech}, series = {2007 IEEE Workshop on Automatic Speech Recognition \& Understanding (ASRU), Kyoto, Japan, December 2007.}, booktitle = {2007 IEEE Workshop on Automatic Speech Recognition \& Understanding (ASRU), Kyoto, Japan, December 2007.}, pages = {717 -- 722}, year = {2007}, abstract = {For many aspects of speech therapy an objective evaluation of the intelligibility of a patient's speech is needed. We investigate the evaluation of the intelligibility of speech by means of automatic speech recognition. Previous studies have shown that measures like word accuracy are consistent with human experts' ratings. To ease the patient's burden, it is highly desirable to conduct the assessment via phone. However, the telephone channel influences the quality of the speech signal which negatively affects the results. To reduce inaccuracies, we propose a combination of two speech recognizers. Experiments on two sets of pathological speech show that the combination results in consistent improvements in the correlation between the automatic evaluation and the ratings by human experts. Furthermore, the approach leads to reductions of 10\% and 25\% of the maximum error of the intelligibility measure.}, language = {en} } @inproceedings{HaderleinRiedhammerMaieretal.2007, author = {Haderlein, Tino and Riedhammer, Korbinian and Maier, Andreas and N{\"o}th, Elmar and Toy, Hikmet and Rosanowski, Frank}, title = {An Automatic Version of the Post-Laryngectomy Telephone Test}, series = {TSD 2007, 10th International Conference on Text, Speech and Dialogue, Proceedings, Pilsen, Czech Republic, September 2007.}, booktitle = {TSD 2007, 10th International Conference on Text, Speech and Dialogue, Proceedings, Pilsen, Czech Republic, September 2007.}, publisher = {Springer-Verlag}, pages = {238 -- 245}, year = {2007}, abstract = {Tracheoesophageal (TE) speech is a possibility to restore the ability to speak after total laryngectomy, i.e. the removal of the larynx. The quality of the substitute voice has to be evaluated during therapy. For the intelligibility evaluation of German speakers over telephone, the Post-Laryngectomy Telephone Test (PLTT) was defined. Each patient reads out 20 of 400 different monosyllabic words and 5 out of 100 sentences. A human listener writes down the words and sentences understood and computes an overall score. This paper presents a means of objective and automatic evaluation that can replace the subjective method. The scores of 11 na{\"i}ve raters for a set of 31 test speakers were compared to the word recognition rate of speech recognizers. Correlation values of about 0.9 were reached.}, language = {en} } @inproceedings{NoethMaierHaderleinetal.2007, author = {N{\"o}th, Elmar and Maier, Andreas and Haderlein, Tino and Riedhammer, Korbinian and Rosanowski, Frank and Schuster, Maria}, title = {Automatic Evaluation of Pathologic Speech - from Research to Routine Clinical Use}, series = {TSD 2007, 10th International Conference on Text, Speech and Dialogue, Pilsen, Czech Republic, September 2007.}, booktitle = {TSD 2007, 10th International Conference on Text, Speech and Dialogue, Pilsen, Czech Republic, September 2007.}, publisher = {Springer-Verlag}, pages = {294 -- 301}, year = {2007}, abstract = {Previously we have shown that ASR technology can be used to objectively evaluate pathologic speech. Here we report on progress for routine clinical use: 1) We introduce an easy-to-use recording and evaluation environment. 2) We confirm our previous results for a larger group of patients. 3) We show that telephone speech can be analyzed with the same methods with only a small loss of agreement with human experts. 4) We show that prosodic information leads to more robust results. 5) We show that text reference instead of transliteration can be used for evaluation. Using word accuracy of a speech recognizer and prosodic features as features for SVM regression, we achieve a correlation of .90 between the automatic analysis and human experts.}, language = {en} } @inproceedings{HaderleinEysholdtRiedhammeretal.2007, author = {Haderlein, Tino and Eysholdt, Ulrich and Riedhammer, Korbinian and N{\"o}th, Elmar and Rosanowski, Frank}, title = {Automatisierung des Postlaryngektomie-Telefontests (PLTT)}, series = {Aktuelle phoniatrisch-p{\"a}daudiologische Aspekte}, booktitle = {Aktuelle phoniatrisch-p{\"a}daudiologische Aspekte}, pages = {66 -- 69}, year = {2007}, abstract = {In fr{\"u}heren Arbeiten wurde gezeigt, dass automatische Spracherkennungsverfahren verwendet werden k{\"o}nnen, um die Verst{\"a}ndlichkeit von Sprechern mit tracheo{\"o}sophagealer Ersatzstimme (TE-Stimme) automatisch zu bewerten [1,2]. In diesem Beitrag wird eine automatische Version des Postlaryngektomie-Telefontests (PLTT, [3]) vorgestellt, der einen eingef{\"u}hrten Standardtest f{\"u}r die Verst{\"a}ndlichkeit {\"u}ber das Telefon darstellt.}, language = {de} } @inproceedings{RiedhammerHaderleinSchusteretal.2006, author = {Riedhammer, Korbinian and Haderlein, Tino and Schuster, Maria and Rosanowski, Frank and N{\"o}th, Elmar}, title = {Automatic Evaluation of Tracheoesophageal Telephone Speech}, series = {First International Language Technologies Conference (IS-LTC 2006), Ljubljana, Slovenia, October 2006.}, booktitle = {First International Language Technologies Conference (IS-LTC 2006), Ljubljana, Slovenia, October 2006.}, pages = {17 -- 22}, year = {2006}, abstract = {The tracheoesophageal (TE) substitute voice is currently state-of-the-art treatment to restore the ability to speak after laryngectomy. The intelligibility while talking over a telephone is an important clinical factor, as it is a crucial part of the patients' social life. An objective way to rate the intelligibility of substitute voices when talking over a telephone is desirable to improve the post-laryngectomy speech therapy. An automatic speech recognition (ASR) system was applied to 41 high quality recordings of post-laryngectomy patients. The ASR system was trained with normal, non-pathologic speech. It yielded a word accuracy (WA) of 36.9\%±18.0\%; compared to the intelligibility rating of a group of human experts the ASR system had a correlation coefficient of -.88. After downsampling the 41 recordings to telephone quality, the ASR system reached a WA of 26.4\%±13.9\% leading to a correlation coefficient of -.80. These results confirm that an ASR system can be used for objective intelligibility rating over the telephone.}, language = {en} } @inproceedings{RiedhammerHaderleinNoethetal.2006, author = {Riedhammer, Korbinian and Haderlein, Tino and N{\"o}th, Elmar and Toy, Hikmet and Eysholdt, Ulrich and Rosanowski, Frank}, title = {Die tracheo{\"o}sophageale Ersatzstimme: Automatische Verst{\"a}ndlichkeitsbewertung {\"u}ber das Telefon}, series = {23. Wissenschaftliche Jahrestagung der Deutschen Gesellschaft f{\"u}r Phoniatrie und P{\"a}daudiologie. Heidelberg, September 2006. Aktuelle phoniatrisch-p{\"a}daudiologische Aspekte.}, booktitle = {23. Wissenschaftliche Jahrestagung der Deutschen Gesellschaft f{\"u}r Phoniatrie und P{\"a}daudiologie. Heidelberg, September 2006. Aktuelle phoniatrisch-p{\"a}daudiologische Aspekte.}, pages = {51 -- 53}, year = {2006}, abstract = {Die tracheo{\"o}sophageale Ersatzstimme TE ist heute "state of the art" der Stimmrehabilitation nach einer Laryngektomie. In dieser Studie, einem Teilprojekt eines von der Deutschen Krebshilfe gef{\"o}rderten Forschungsvorhabens, ging es um die objektive Bewertung des Behandlungsfortschritts. Untersucht wurden 41 Laryngektomierte mit einer TE (Provox-Stimmventilprothese) durchgef{\"u}hrt. Ziel der Studie war es, die Verst{\"a}ndlichkeit im Gespr{\"a}ch und am Telefon objektiv zu beurteilen und zu vergleichen, um den Patienten in der Zukunft die telefonische Evaluation von zuhause aus zu erm{\"o}glichen. Zur Bewertung diente ein f{\"u}r Marktzwecke professionalisiertes automatisches Spracherkennungssystem. Es wurden zun{\"a}chst Nahbesprechungsaufnahmen des "Nordwind und Sonne"-Textes von f{\"u}nf Experten hinsichtlich ihrer Verst{\"a}ndlichkeit beurteilt. Aus diesen Aufnahmen entstanden durch Abspielen {\"u}ber ein Telefon simulierte Telefonaufnahmen. Zielkriterium der automatischen Analyse war die Wortakkuratheit WA, die mit der an Schulnoten orientierten Stimmbewertung durch die Experten korreliert wurde. Die Studie ergab eine Korrelation von -0,82 f{\"u}r die Nahbesprechungs- und -0,69 f{\"u}r die Telefonaufnahmen. Die Ergebnisse zeigen, dass die automatische Verst{\"a}ndlichkeitsbewertung von Ersatzstimmen auch per Telefon prinzipiell m{\"o}glich ist. M{\"o}glichkeiten, die Qualit{\"a}tsverluste durch die Telefon{\"u}bertragung und die somit niedrigere Korrelation zu kompensieren, werden aufgezeigt.}, language = {de} } @book{Riedhammer2012, author = {Riedhammer, Korbinian}, title = {Interactive Approaches to Video Lecture Assessment}, publisher = {Logos Verlag Berlin GmbH}, address = {Berlin}, publisher = {Technische Hochschule Rosenheim}, year = {2012}, abstract = {Folks that have been here last winter prior to ASRU might be familiar with the title of that talk. But don't be misled, I'll have something new for you. In this talk, I will give an overview over the FAU Lecture Browser which I developed in the context of my thesis. I will start out with the description of a novel data set: The LME Lectures are a corpus of two series of graduate level computer science lectures with 18 recordings each. The courses cover topics in medical image processing and pattern analysis/machine learning. The roughly 40 hours of speech were manually transcribed, and one particular lecture was annotated with key phrases by five human raters. Using this data set, I trained three different speech recognizers using regular continuous, multi-codebook semi-continuous and subspace Gaussian mixture models, that show an error rate of about 10\% WER. I will then briefly describe the key phrase extraction and automatic ranking, which was then compared against five raters on one lecture recording. Finally, I will talk about a little usability study where 10 students were asked to perform a certain task-- with and without the proposed lecture browser. Although the number of contestants is limited, the numbers are interesting: the users that had the interface could complete the tasks about 30\% faster than the control group, while maintaining about the same accuracy.}, language = {en} } @book{Riedhammer2008, author = {Riedhammer, Korbinian}, title = {An Automatic Intelligibility Test Based on the Post-Laryngectomy Telephone Test}, publisher = {Mueller Verlag}, address = {N{\"u}rnberg}, publisher = {Technische Hochschule Rosenheim}, year = {2008}, language = {en} } @book{Schildt2007, author = {Schildt, Herbert}, title = {C/C++ GE-PACKT}, editor = {Riedhammer, Korbinian}, edition = {3. Auflage}, publisher = {Mitp-Verlag}, address = {Frechen bei K{\"o}ln}, publisher = {Technische Hochschule Rosenheim}, year = {2007}, language = {de} } @book{Schildt2007, author = {Schildt, Herbert}, title = {++ Die professionelle Referenz. IT-Studienausgabe}, editor = {Riedhammer, Korbinian}, edition = {2. Auflage}, publisher = {Mitp-Verlag}, address = {Frechen bei K{\"o}ln}, publisher = {Technische Hochschule Rosenheim}, year = {2007}, language = {de} } @article{HaderleinRiedhammerNoethetal.2008, author = {Haderlein, Tino and Riedhammer, Korbinian and N{\"o}th, Elmar and Toy, Hikmet and Schuster, Maria and Eysholdt, Ulrich and Hornegger, Joachim and Rosanowski, Frank}, title = {Application of Automatic Speech Recognition to Quantitative Assessment of Tracheoesophageal Speech in Different Signal Quality}, series = {Folia Phoniatrica Et Logopaedica}, volume = {2008}, journal = {Folia Phoniatrica Et Logopaedica}, number = {61(1)}, pages = {12 -- 17}, year = {2008}, abstract = {Tracheoesophageal voice is state-of-the-art in voice rehabilitation after laryngectomy. Intelligibility on a telephone is an important evaluation criterion as it is a crucial part of social life. An objective measure of intelligibility when talking on a telephone is desirable in the field of postlaryngectomy speech therapy and its evaluation. Based upon successful earlier studies with broadband speech, an automatic speech recognition (ASR) system was applied to 41 recordings of postlaryngectomy patients. Recordings were available in different signal qualities; quality was the crucial criterion for this study. Compared to the intelligibility rating of 5 human experts, the ASR system had a correlation coefficient of r = -0.87 and Krippendorff's alpha of 0.65 when broadband speech was processed. The rater group alone achieved alpha = 0.66. With the test recordings in telephone quality, the system reached r = -0.79 and alpha = 0.67. For medical purposes, a comprehensive diagnostic approach to (substitute) voice has to cover both subjective and objective tests. An automatic recognition system such as the one proposed in this study can be used for objective intelligibility rating with results comparable to those of human experts. This holds for broadband speech as well as for automatic evaluation via telephone.}, language = {en} } @article{BockletRiedhammerNoethetal.2012, author = {Bocklet, Tobias and Riedhammer, Korbinian and N{\"o}th, Elmar and Eysholdt, Ulrich and Haderlein, Tino}, title = {Automatic Intelligibility Assessment of Speakers After Laryngeal Cancer by Means of Acoustic Modeling}, series = {Journal of Voice}, journal = {Journal of Voice}, number = {26(3)}, pages = {390 -- 397}, year = {2012}, abstract = {One aspect of voice and speech evaluation after laryngeal cancer is acoustic analysis. Perceptual evaluation by expert raters is a standard in the clinical environment for global criteria such as overall quality or intelligibility. So far, automatic approaches evaluate acoustic properties of pathologic voices based on voiced/unvoiced distinction and fundamental frequency analysis of sustained vowels. Because of the high amount of noisy components and the increasing aperiodicity of highly pathologic voices, a fully automatic analysis of fundamental frequency is difficult. We introduce a purely data-driven system for the acoustic analysis of pathologic voices based on recordings of a standard text.}, language = {en} } @article{RiedhammerFavreHakkaniTuer2010, author = {Riedhammer, Korbinian and Favre, Benoit and Hakkani-T{\"u}r, Dilek}, title = {Long story short - Global unsupervised models for keyphrase based meeting summarization}, series = {SPEECH COMMUNICATION}, volume = {2010}, journal = {SPEECH COMMUNICATION}, number = {52(10)}, pages = {801 -- 815}, year = {2010}, language = {en} } @article{TurStolckeVossetal.2010, author = {Tur, Gokhan and Stolcke, Andreas and Voss, Lynn and Peters, Stanley and Hakkani-T{\"u}r, Dilek and Dowding, John and Favre, Benoit and Fernandez, Raquel and Frampton, Matthew and Frandsen, Michael and Frederickson, Clint and Graciarena, Martin and Kintzing, Donald and Leveque, Kyle and Mason, Shane and Niekrasz, John and Purver, Matthew and Riedhammer, Korbinian and Shriberg, Elizabeth and Tien, Jing and Vergyri, Dimitra and Yang, Fan}, title = {The CALO Meeting Assistant System}, series = {IEEE Transactions on Audio, Speech and Language Processing}, volume = {2010}, journal = {IEEE Transactions on Audio, Speech and Language Processing}, number = {18(6)}, pages = {1601 -- 1611}, year = {2010}, abstract = {The CALO Meeting Assistant (MA) provides for distributed meeting capture, annotation, automatic transcription and semantic analysis of multiparty meetings, and is part of the larger CALO personal assistant system. This paper presents the CALO-MA architecture and its speech recognition and understanding components, which include real-time and offline speech transcription, dialog act segmentation and tagging, topic identification and segmentation, question-answer pair identification, action item recognition, decision extraction, and summarization.}, language = {en} } @article{HaderleinRiedhammerMaieretal.2009, author = {Haderlein, Tino and Riedhammer, Korbinian and Maier, Andreas and N{\"o}th, Elmar and Eysholdt, Ulrich and Rosanowski, Frank}, title = {Automatisierung des Postlaryngektomie-Telefontests}, series = {HNO}, volume = {2009}, journal = {HNO}, number = {57}, publisher = {Springer-Verlag}, pages = {51 -- 56}, year = {2009}, abstract = {In dieser Studie wird ein objektives Verfahren f{\"u}r die Verst{\"a}ndlichkeitsmessung mit dem Postlaryngektomie-Telefontest (PLTT) mittels automatischer Spracherkennungstechnik beschrieben. 31 Sprecher mit tracheo{\"o}sophagealer Ersatzstimme (25 M{\"a}nner und 6 Frauen; 63,4±8,7 Jahre) wurden zun{\"a}chst von 11 naiven H{\"o}rern bewertet. Der vom Spracherkennungssystem ermittelte Verst{\"a}ndlichkeitsgrad wird als Prozentsatz korrekt verstandener W{\"o}rter einer Wortkette, der Wortakkuratheit bzw. -korrektheit, angegeben und mit den subjektiv ermittelten PLTT-Werten verglichen. Die durchschnittliche PLTT-Gesamtverst{\"a}ndlichkeit der 11 naiven H{\"o}rer liegt bei 47\%, die automatisch ermittelte Wortakkuratheit und Wortkorrektheit liegen deutlich niedriger (etwa 0\% bzw. etwa 15\%). Die Korrelation zwischen menschlicher und maschineller Bewertung liegt jedoch z. T. {\"u}ber 0,9. F{\"u}r den Gesamtverst{\"a}ndlichkeitswert des PLTT kann mit Hilfe der automatischen Spracherkennung objektiv und effizient ein {\"a}quivalentes Maß berechnet werden.}, language = {de} } @book{ErnstSchmidtBeneken2016, author = {Ernst, H. and Schmidt, Jochen and Beneken, Gerd}, title = {Grundkurs Informatik: Grundlagen und Konzepte f{\"u}r die erfolgreiche IT-Praxis - Eine umfassende, praxisorientierte Einf{\"u}hrung}, publisher = {Springer Vieweg}, address = {Berlin}, publisher = {Technische Hochschule Rosenheim}, year = {2016}, abstract = {Zahlensysteme und bin{\"a}re Arithmetik Nachricht und Information Codierung und Datenkompression Verschl{\"u}sselung Schaltalgebra, Schaltnetze und Elemente der Computerhardware Rechnerarchitekturen Rechnernetze Betriebssysteme Datenbanken Automatentheorie und formale Sprachen Berechenbarkeit und Komplexit{\"a}t Suchen und Sortieren B{\"a}ume und Graphen prozedurale und objektorientierte Programmierung (C und Java) Anwendungsprogrammierung im Internet (HTML, CSS, JavaScript und PHP) Software-Engineering}, language = {de} } @inproceedings{ZengerSchmidtKroedel2013, author = {Zenger, A. and Schmidt, Jochen and Kr{\"o}del, M.}, title = {Towards the Intelligent Home: Using Reinforcement-Learning for Optimal Heating Control}, series = {Advances in Artificial Intelligence, Proceedings of the 36th Annual Conference on AI, volume 8077 of Lecture Notes in Artificial Intelligence}, booktitle = {Advances in Artificial Intelligence, Proceedings of the 36th Annual Conference on AI, volume 8077 of Lecture Notes in Artificial Intelligence}, publisher = {Springer}, year = {2013}, abstract = {We propose a reinforcement learning approach to heating control in home automation, that can acquire a set of rules enabling an agent to heat a room to the desired temperature at a defined time while conserving as much energy as possible. Experimental results are presented that show the feasibility of our method.}, language = {en} } @article{DarmsFoelsterSchmidtetal.2010, author = {Darms, M. and F{\"o}lster, F. and Schmidt, Jochen and Fr{\"o}hlich, D. and Eckert, A.}, title = {Data Fusion Strategies in Advanced Driver Assistance Systems}, series = {SAE International Journal of Passenger Cars - Electronic and Electrical Systems}, journal = {SAE International Journal of Passenger Cars - Electronic and Electrical Systems}, year = {2010}, abstract = {Data fusion plays a central role in more and more automotive applications, especially for driver assistance systems. On the one hand the process of data fusion combines data and information to estimate or predict states of observed objects. On the other hand data fusion introduces abstraction layers for data description and allows building more flexible and modular systems.The data fusion process can be divided into a low-level processing (tracking and object discrimination) and a high level processing (situation assessment). High level processing becomes more and more the focus of current research as different assistance applications will be combined into one comprehensive assistance system. Different levels/strategies for data fusion can be distinguished: Fusion on raw data level, fusion on feature level and fusion on decision level. All fusion strategies can be found in current driver assistance implementations. The paper gives an overview of the different fusion strategies and shows their application in current driver assistance systems. For low level processing a raw data fusion approach in a stereo video system is described, as an example for feature level fusion the fusion of radar and camera data for tracking is explained. As an example for a high level fusion algorithm an approach for a situation assessment based on multiple sensors is given. The paper describes practical realizations of these examples and points out their potential to further increase traffic safety with reasonably low cost for the overall system.}, language = {en} } @inproceedings{WongYeapSchmidt2009, author = {Wong, C.K. and Yeap, W.K. and Schmidt, Jochen}, title = {Our Next Generation of Robotics Researchers? Teaching Robotics at Primary School Level.}, series = {Readings in Technology and Education: Proceedings of International Conference on Information Communication Technologies in Education}, booktitle = {Readings in Technology and Education: Proceedings of International Conference on Information Communication Technologies in Education}, year = {2009}, abstract = {In this paper, we present our experience in designing and teaching of our first robotics course for students at primary school level. The course was carried out over a comparatively short period of time, namely 6 weeks, 2 hours per week. In contrast to many other projects, we use robots that researchers used to conduct their research and discuss problems faced by these researchers. Thus, this is not a behavioural study but a hands-on learning experience for the students. The aim is to highlight the development of autonomous robots and artificial intelligence as well as to promote science and robotics in schools.}, language = {de} } @article{SchmidtNiemann2008, author = {Schmidt, Jochen and Niemann, H.}, title = {Data Selection for Hand-eye Calibration: A Vector Quantization Approach}, series = {The International Journal of Robotics Research}, journal = {The International Journal of Robotics Research}, year = {2008}, abstract = {This paper presents new vector quantization based methods for selecting well-suited data for hand-eye calibration from a given sequence of hand and eye movements. Data selection can improve the accuracy of classic hand-eye calibration, and make it possible in the first place in situations where the standard approach of manually selecting positions is inconvenient or even impossible, especially when using continuously recorded data. A variety of methods is proposed, which differ from each other in the dimensionality of the vector quantization compared to the degrees of freedom of the rotation representation, and how the rotation angle is incorporated. The performance of the proposed vector quantization based data selection methods is evaluated using data obtained from a manually moved optical tracking system (hand) and an endoscopic camera (eye).}, language = {en} } @incollection{YeapWongSchmidt2008, author = {Yeap, W.K. and Wong, C.K. and Schmidt, Jochen}, title = {Using a Mobile Robot to Test a Theory of Cognitive Mapping.}, series = {Robotics and Cognitive Approaches to Spatial Mapping, Springer Tracts in Advanced Robotics}, booktitle = {Robotics and Cognitive Approaches to Spatial Mapping, Springer Tracts in Advanced Robotics}, publisher = {Springer}, address = {Berlin}, publisher = {Technische Hochschule Rosenheim}, year = {2008}, abstract = {This paper describes using a mobile robot, equipped with some sonar sensors and an odometer, to test navigation through the use of a cognitive map. The robot explores an office environment, computes a cognitive map, which is a network of ASRs [36, 35], and attempts to find its way home. Ten trials were conducted and the robot found its way home each time. From four random positions in two trials, the robot estimated the home position relative to its current position reasonably accurately. Our robot does not solve the simultaneous localization and mapping problem and the map computed is fuzzy and inaccurate with much of the details missing. In each homeward journey, it computes a new cognitive map of the same part of the environment, as seen from the perspective of the homeward journey. We show how the robot uses distance information from both maps to find its way home.}, language = {en} } @inproceedings{SchmidtWongYeap2007, author = {Schmidt, Jochen and Wong, C.K. and Yeap, W.K.}, title = {Spatial Information Extraction for Cognitive Mapping with a Mobile Robot.}, series = {Conference on Spatial Information Theory: COSIT'07, Melbourne, Australia. Volume 4736 of Lecture Notes in Computer Science}, booktitle = {Conference on Spatial Information Theory: COSIT'07, Melbourne, Australia. Volume 4736 of Lecture Notes in Computer Science}, year = {2007}, abstract = {When animals (including humans) first explore a new environment, what they remember is fragmentary knowledge about the places visited. Yet, they have to use such fragmentary knowledge to find their way home. Humans naturally use more powerful heuristics while lower animals have shown to develop a variety of methods that tend to utilize two key pieces of information, namely distance and orientation information. Their methods differ depending on how they sense their environment. Could a mobile robot be used to investigate the nature of such a process, commonly referred to in the psychological literature as cognitive mapping? What might be computed in the initial explorations and how is the resulting "cognitive map" be used for localization? In this paper, we present an approach using a mobile robot to generate a "cognitive map", the main focus being on experiments conducted in large spaces that the robot cannot apprehend at once due to the very limited range of its sensors. The robot computes a "cognitive map" and uses distance and orientation information for localization.}, language = {en} } @article{SchmidtWongYeap2007, author = {Schmidt, Jochen and Wong, C.K. and Yeap, W.K.}, title = {Localisation and Mapping with a Mobile Robot Using Sparse Range Data}, series = {Autonomous Robots and Agents, Studies in Computational Intelligence (SCI),}, journal = {Autonomous Robots and Agents, Studies in Computational Intelligence (SCI),}, publisher = {Springer}, year = {2007}, abstract = {We present an approach for indoor mapping and localisation using sparse range data, acquired by a mobile robot equipped with sonar sensors. The chapter consists of two main parts. First, a split and merge based method for dividing a given metric map into distinct regions is presented, thus creating a topological map in a metric framework. Spatial information extracted from this map is then used for self-localisation on the return home journey. The robot computes local confidence maps for two simple localisation strategies based on distance and relative orientation of regions. These local maps are then fused to produce overall confidence maps.}, language = {de} } @inproceedings{WongYeapSchmidt2007, author = {Wong, C.K. and Yeap, W.K. and Schmidt, Jochen}, title = {Using a Mobile Robot for Cognitive Mapping}, series = {International Joint Conference on Artificial Intelligence (IJCAI), pages 2243-2248, Hyderabad, India, 2007}, booktitle = {International Joint Conference on Artificial Intelligence (IJCAI), pages 2243-2248, Hyderabad, India, 2007}, year = {2007}, abstract = {When animals (including humans) first explore a new environment, what they remember is fragmentary knowledge about the places visited. Yet, they have to use such fragmentary knowledge to find their way home. Humans naturally use more powerful heuristics while lower animals have shown to developa varietyof methodsthat tend to utilize two key pieces of information,namely distance and orientation information. Their methods differ depending on how they sense their environment. Could a mobile robot be used to investigate the nature of such a process, commonly referred to in the psychological literature as cognitive mapping? What might be computed in the initial explorations and how is the resulting "cognitive map" be used to return home? In this paper, we presented a novel approach using a mobile robot to do cognitive mapping. Our robot computes a "cognitive map" and uses distance and orientation information to find its way home. The process developed provides interesting insights into the nature of cognitive mapping and encourages us to use a mobile robot to do cognitive mapping in the future, as opposed to its popular use in robot mapping.}, language = {en} } @book{Schmidt2006, author = {Schmidt, Jochen}, title = {3-D Reconstruction and Stereo Self-Calibration for Augmented Reality}, publisher = {Logos}, address = {Berlin}, publisher = {Technische Hochschule Rosenheim}, year = {2006}, abstract = {The main focus of this work is the development of new methods for the self-calibration of a rigid stereo camera system. However, many of the algorithms introduced here have a wider impact, particularly in robot hand-eye calibration with all its different areas of application. Stereo self-calibration refers to the computation of the intrinsic and extrinsic parameters of a stereo rig using neither a priori knowledge on the movement of the rig nor on the geometry of the observed scene. The stereo parameters obtained by self-calibration, namely rotation and translation from left to right camera, are used for computing depth maps for both images, which are applied for rendering correctly occluded virtual objects into a real scene (Augmented Reality). The proposed methods were evaluated on real and synthetic data and compared to algorithms from the literature. In addition to a stereo rig, an optical tracking system with a camera mounted on an endoscope was calibrated without a calibration pattern using the proposed extended hand-eye calibration algorithm. The self-calibration methods developed in this work have a number of features, which make them easily applicable in practice: They rely on temporal feature tracking only, as this monocular tracking in a continuous image sequence is much easier than left-to-right tracking when the camera parameters are still unknown. Intrinsic and extrinsic camera parameters are computed during the self-calibration process, i.e., no calibration pattern is required. The proposed stereo self-calibration approach can also be used for extended hand-eye calibration, where the eye poses are obtained by structure-from-motion rather than from a calibration pattern. An inherent problem to hand-eye calibration is that it requires at least two general movements of the cameras in order to compute the rigid transformation. If the motion is not general enough, only a part of the parameters can be obtained, which would not be sufficient for computing depth maps. Therefore, a main part of this work discusses methods for data selection that increase the robustness of hand-eye calibration. Different new approaches are shown, the most successful ones being based on vector quantization. The data selection algorithms developed in this work can not only be used for stereo self-calibration, but also for classic robot hand-eye calibration, and they are independent of the actually used hand-eye calibration algorithm.}, language = {en} } @inproceedings{ZinsserSchmidtNiemann2003, author = {Zinßer, T. and Schmidt, Jochen and Niemann, H.}, title = {Performance Analysis of Nearest Neighbor Algorithms for ICP Registration of 3-D Point Sets}, series = {Vision, Modeling, and Visualization 2003}, booktitle = {Vision, Modeling, and Visualization 2003}, year = {2003}, abstract = {There are many nearest neighbor algorithms tailor made for ICP,but most of them require Special input data like range Images or triangle meshes. We focus on efficient nearest neighbor algorithms that do not impose this limitation, and thus can also be used with 3-D point sets generated by structure-frommotion techniques. We shortly present the evaluated algorithms and introduce the modifications we made to improve their efficiency. In particular, several enhancements to the well-known k-D tree algorithm are described. The first part of our Performance Analysis consists of Experiments on synthetic point sets, whereas the second part features experiments with the ICP algorithm on real point sets. Both parts are completed by a thorough evaluation of the obtained results.}, language = {en} } @article{ZobelDenzlerHeigletal.2003, author = {Zobel, M. and Denzler, J. and Heigl, B. and N{\"o}th, E. and Paulus, D. and Schmidt, Jochen and Stemmer, G.}, title = {MOBSY: Integration of vision and dialogue in service robots}, series = {Machine Vision and Applications}, journal = {Machine Vision and Applications}, year = {2003}, abstract = {This contribution introduces MOBSY, a fully integrated, autonomous mobile service robot system. It acts as an automatic dialogue-based receptionist for visitors to our institute. MOBSY incorporates many techniques from different research areas into one working stand-alone system. The techniques involved range from computer vision over speech understanding to classical robotics. Along with the two main aspects of vision and speech, we also focus on the integration aspect, both on the methodological and on the technical level. We describe the task and the techniques involved. Finally, we discuss the experiences that we gained with MOBSY during a live performance at our institute.}, language = {en} } @inproceedings{WenhardtSchmidtNiemann2002, author = {Wenhardt, S. and Schmidt, Jochen and Niemann, H.}, title = {Didaktische Aufbereitung von Methoden des Rechnersehens f{\"u}r virtuelle Vorlesungen}, series = {Forschungsbeitr{\"a}ge zur Didaktik der Informatik - Theorie, Praxis, Evaluation}, booktitle = {Forschungsbeitr{\"a}ge zur Didaktik der Informatik - Theorie, Praxis, Evaluation}, year = {2002}, abstract = {Dieser Artikel stellt ein Konzept f¨ur eine Online-Vorlesung im Rahmen der virtuellen Hochschule Bayern vor. Zun{\"a}chst werden kurz die fachlichen Inhalte erl¨autert, die es zu vermitteln gilt. Nach dieser Einf{\"u}hrung wird auf die Umsetzung der Inhalte in eine dem neuen Medium Internet angemessene Form eingegangen. Dies betrifft vor allem die ausgew{\"a}hlten Techniken, die zur Wissensvermittlung eingesetzt werden. Ein besonderer Schwerpunkt liegt auf der M{\"o}glichkeit durch Interaktivit{\"a}t das Wissen experimentell zu vertiefen und somit eine Verbindung zwischen dem theoretisch Gelernten und dem praktisch Erfahrenen herzustellen. Weiterhin wird eine Vielfalt an Kommunikationsm¨oglichkeiten vorgestellt, da Kommunikation eine wichtige soziale Komponente im Lernprozess und h¨aufig entscheidend f¨ur den Erfolg ist.}, language = {de} } @inproceedings{SchmidtVogtNiemann2002, author = {Schmidt, Jochen and Vogt, F. and Niemann, H.}, title = {Nonlinear Refinement of Camera Parameters using an Endoscopic Surgery Robot}, series = {Proceedings of IAPR Conference on Machine Vision Applications (MVA)}, booktitle = {Proceedings of IAPR Conference on Machine Vision Applications (MVA)}, year = {2002}, abstract = {We present an Approach for non linea roptimization of the parameters of an endoscopic camera mounted on a surgery robot. The goal is to generate a depth map for each image in order to enhance the quality of medical light fields. The pose information provided by the robot is used as an initialization, where especially the orientation isi naccurate. Refinement of intrinsic and extrinsic camera parameters is performed by minimizing the back-projectionerror of 3-D points that are reconstructed by triangulation from image Feature stracked over an image sequence. Optimization of the camera parameters results in an enhancement of Rendering Quality in two ways: More accurate parameters lead to better interpolation as well as to better depth maps for approximating the scenegeometry.}, language = {en} } @inproceedings{SchmidtNiemannVogt2002, author = {Schmidt, Jochen and Niemann, H. and Vogt, F.}, title = {Dense Disparity Maps in Real-Time with an Application to Augmented Reality}, series = {Proceedings Sixth IEEE Workshop on Applications of Computer Vision (WACV 2002), pages 225-230, Orlando, FL USA}, booktitle = {Proceedings Sixth IEEE Workshop on Applications of Computer Vision (WACV 2002), pages 225-230, Orlando, FL USA}, year = {2002}, abstract = {This work presents a technique for computing dense disparity maps from a binocular stereo camera system. The methods are applied in an Augmented Reality setting for combining real and virtual worlds with proper occlusions. The proposed stereo correspondence technique is based oil area matching and facilitates an efficient strategy by using the concept of a three-dimensional similarity accumulator whereby occlusions are detected and object boundaries are extracted correctly. The main contribution of this paper is the way we fill the accumulator using absolute differences of images and computing a mean filter on these difference images. This. is. where the main advantages of the accumulator approach can be exploited, since all entries can be computed in parallel and thus extremely efficient. Additionally, we-perform an asymmetric correction step and a post-processing of the disparity maps that maintains object edges.}, language = {en} } @inproceedings{SchmidtNiemann2002, author = {Schmidt, Jochen and Niemann, H.}, title = {Using Quaternions for Parametrizing 3D Rotations in Unconstrained Nonlinear Optimization}, series = {Vision, Modeling, and Visualization 2001, pages 399-406, Stuttgart, Germany}, booktitle = {Vision, Modeling, and Visualization 2001, pages 399-406, Stuttgart, Germany}, year = {2002}, abstract = {In this paper we address the problem of using quaternions in unconstrained nonlinear optimization of 3-D rotations. Quaternions representing rotations have four elements but only three degrees of freedom, since they must be of norm one. This constraint has to be taken into account when applying e.g. the Levenberg-Marquardt algorithm, a method for unconstrained nonlinear optimization widely used in computer vision. We propose an easy to use method for achieving this. Experiments using our parametrization in photo grammetric b{\"u}ndle -adjustment are presented at the end of the paper.}, language = {en} } @inproceedings{SchmidtScholzNiemann2001, author = {Schmidt, Jochen and Scholz, I. and Niemann, H.}, title = {Placing Arbitrary Objects in a Real Scene Using a Color Cube for Pose Estimation}, series = {Pattern Recognition, 23rd DAGM Symposium}, booktitle = {Pattern Recognition, 23rd DAGM Symposium}, year = {2001}, abstract = {We describe an Augmented Reality system using the corners of a color cube for camera calibration. In the augmented image the cube is replaced by a computer generated virtual object. The cube is localized in an image by the CSC color segmentation algorithm. The camera projection matrix is estimated with a linear method that is followed by a nonlinear refinement step. Because of possible missclassifications of the segmented color regions and the minimum number of point correspondences used for calibration, the estimated pose of the cube may be very erroneous for some frames; therefore we perform outlier detection and treatment for rendering the virtual object in an acceptable manner.}, language = {en} } @inproceedings{ScholzSchmidtNiemann2001, author = {Scholz, I. and Schmidt, Jochen and Niemann, H.}, title = {Farbbildverarbeitung unter Echtzeitbedingungen in der Augmented Reality}, series = {Workshop Farbbildverarbeitung, pages 59-65, Erlangen, Germany, 4.-5. Oktober 2001. Universit{\"a}t Erlangen-N{\"u}rnberg, Institut f{\"u}r Informatik}, booktitle = {Workshop Farbbildverarbeitung, pages 59-65, Erlangen, Germany, 4.-5. Oktober 2001. Universit{\"a}t Erlangen-N{\"u}rnberg, Institut f{\"u}r Informatik}, year = {2001}, abstract = {Es wird ein System aus der Augmented Reality (Erweiterte Reali{\"a}at, AR) vorgestellt, das zur Kamerakalibrierung einen farbigen W{\"u}rfel verwendet, der außerdem als Platzhalter f{\"u}r ein virtuelles Objekt dient. Zur Erkennung des W{\"u}rfels in einer Szene werden Methoden aus der Farbbildverarbeitung verwendet, wie der Color Structure Code (CSC) und die Klassifikation der entstehenden Regionen nach ihrer Farbe. Zur Beschleunigung der Segmentierung wird ein hierarchisches Verfahren eingesetzt.}, language = {de} } @article{ZobelDenzlerHeigletal.2001, author = {Zobel, M. and Denzler, J. and Heigl, B. and N{\"o}th, E. and Paulus, D. and Schmidt, Jochen and Stemmer, G.}, title = {Demonstration von Bildverarbeitung und Sprachverstehen in der Dienstleistungsrobotik}, series = {Autonome Mobile Systeme}, journal = {Autonome Mobile Systeme}, year = {2001}, abstract = {Die typischerweise gew{\"u}nschten Einsatzgebiete f{\"u}r Dienstleistungsroboter, z. B. Krankenh{\"a}user oder Seniorenheime, stellen sehr hohe Anforderungen an die Mensch-Maschine-Schnittstelle. Diese Erfordernisse gehen im Allgemeinen {\"u}ber die M{\"o}glichkeiten der Standardsensoren, wie Ultraschalloder Infrarotsensoren, hinaus. Es m{\"u}ssen daher erg{\"a}nzende Verfahren zum Einsatz kommen. Aus der Sicht der Mustererkennung sind die Nutzung des Rechnersehens und des nat{\"u}rlichsprachlichen Dialogs von besonderem Interesse. Dieser Beitrag stellt das mobile System MOBS Y vor. MOBS Y ist ein vollkommen integrierter autonomer mobiler Dienstleistungsroboter. Er dient als ein automatischer dialogbasierter Empfangsservice f{\"u}r Besucher unseres Instituts. MOBSY vereinigt vielf{\"a}ltige Methoden aus unterschiedlichsten Forschungsgebieten in einem eigenst{\"a}ndigen System. Die zum Einsatz kommenden Methoden aus dem Bereich der Bildverarbeitung reichen dabei von Objektklassifikation {\"u}ber visuelle Selbstlokalisierung und Rekalibrierung bis hin zu multiokularer Objektverfolgung. Die Dialogkomponente umfasst Methoden der Spracherkennung, des Sprachverstehens und die Generierung von Antworten. Im Beitrag werden die zu erf{\"u}llende Aufgabe und die einzelnen Verfahren dargestellt.}, language = {de} } @inproceedings{ZobelDenzlerHeigletal.2001, author = {Zobel, M. and Denzler, J. and Heigl, B. and N{\"o}th, E. and Paulus, D. and Schmidt, Jochen and Stemmer, G.}, title = {MOBSY: Integration of vision and dialogue in service robots}, series = {Computer Vision Systems, Proceedings Second International Workshop, ICVS 2001, Vancouver, Canada}, booktitle = {Computer Vision Systems, Proceedings Second International Workshop, ICVS 2001, Vancouver, Canada}, year = {2001}, abstract = {MOBSY is a fully integrated autonomous mobile service robot system. It acts as an automatic dialogue based receptionist for visitors of our institute. MOBSY incorporates many techniques from different research areas into one working stand-alone system. Especially the computer vision and dialogue aspects are of main interest from the pattern recognition's point of view. To summarize shortly, the involved techniques range from object classification over visual self-localization and recalibration to object tracking with multiple cameras. A dialogue component has to deal with speech recognition, understanding and answer generation. Further techniques needed are navigation, obstacle avoidance, and mechanisms to provide fault tolerant behavior. This contribution introduces our mobile system MOBSY. Among the main aspects vision and speech, we focus also on the integration aspect, both on the methodological and on the technical level. We describe the task and the involved techniques. Finally, we discuss the experiences that we gained with MOBSY during a live performance at the 25th anniversary of our institute}, language = {en} }