Search our Publications
Latest Publications
Gökhan Ince, Kazuhiro Nakadai, Tobias Rodemann, Hiroshi Tsujino, Jun-ichi Imura , "Multi-talker Speech Recognition under Ego-motion Noise using Missing Feature Theory", IEEE-RSJ International Conference on Intelligent Robot and Systems (IROS 2010), 2010.
Download Bibtex file Download PDF
Alexander Denecke, Irene Ayllón Clemente, Heiko Wersing, Julian Eggert, Jochen Steil , "Figure-ground Segmentation using Metrics Adaptation in Level Set Methods", European Symposium on Artificial Neural Networks (ESANN), 2010.
Download Bibtex file Download PDF
Chen Zhang and Julian Eggert , "Exploiting Hierarchical Prediction Models for Mixed 2D-3D Tracking", European Symposium on Artificial Neural Networks (ESANN), 2010.
AbstractIn this paper, we present a generic way to use a hierarchical representation of prediction models for adaptive tracking. Starting with a basic appearance-based tracker working in 2D retinal space, we show how to combine individual trackers for the left and right eye to a true 3D tracker that is built on top of the 2D trackers. We show how the trackers benefit from the hierarchical structure by dynamical model switching depending on the reliabilit...
Download Bibtex file Download PDF
Robert Kastner, Thomas Michalke, Jannik Fritsch, Christian Goerick , "A Self-Adaptive Approach for Curbstone/Roadside Detection based on Human-Like Signal Processing and Multi-Sensor Fusion", IEEE Intelligent Vehicles Symposium (IV), 2010.
Download Bibtex file Download PDF
Daniel Dornbusch, Robert Haschke, Stefan Menzel, Heiko Wersing , "Correlating Shape and Functional Properties Using Decomposition Approaches", 23rd Florida Artificial Intelligence Research Society Conference (FLAIRS-23), pp. 398 – 403, 2010.
AbstractIn this paper, we propose the application of standard decomposition approaches to find local correlations in multimodal data. In a test scenario, we apply these methods to correlate the local shape of turbine blades with their associated aerodynamic flow fields. We compare several decomposition algorithms, i.e., k-Means, Principal Component Analysis, Non-negative Matrix Factorization and Uni-orthogonal Non-negative Matrix Factorization, with rega...
Download Bibtex file Download PDF
Tobias Rodemann, Martin Ernst Heckmann, Claudius Gläser, Frank Joublin, Christian Goerick , "Towards Speech Acquisition in Natural Interaction on ASIMO", Journal of the Robot Society of Japan, special issue on Robot Audition, vol. 28, no. 1, pp. 18–22, 2010.
AbstractThe standard approach for teaching robots to communicate via speech is by providing the structure, statistics, and semantics of speech through a supervised, offline learning process. This process imposes constraints like a high degree of specialization to certain, predefined tasks. The resulting system is very rigid and lacks the ability to acquire new skills (e.g. words and their semantics). In contrast to this, children acquire language through...
Download Bibtex file Download PDF
Xavier Domont , "Hierarchical Spectro-Temporal Features for Robust Speech Recognition", Technische Universität Darmstadt, 2010.
AbstractAutomatic Speech Recognition (ASR) systems are nowadays integrated into products like computer operating systems, automobiles, or hotlines. ASR system are for instance used by p hysicians for el ectronic medical record where it replaces tr aditional dictation and subsequent secretarial transcription [1]. The survey in [1] shows that the physicians tend to be less enthusiastic with the introduction of the new technology after having used it for so...
Download Bibtex file Per Mail Request
Michael Garcia Ortiz, Alexander Gepperth, Jannik Fritsch , "Autonomous generation of internal representations for associative learning", Artificial Neural Networks - ICANN 2010, 2010.
Download Bibtex file Download PDF
Claudius Gläser and Frank Joublin , "An Adaptive Normalized Gaussian Network and Its Application to Online Category Learning", Proceedings of the International Joint Conference on Neural Networks (IJCNN), IEEE World Congress on Computational Intelligence (WCCI), pp. 675–682, 2010.
AbstractIn online applications, where training samples sequentially arise during execution, incremental learning schemes have to be applied. In this paper we propose an adaptive Normalized Gaussian Network model (NGnet) suitable for incremental learning. Following a statistical account we present a truly sequential training procedure. Key to the learning algorithm are local unit manipulation mechanisms for network growth and pruning which continuously ad...
Download Bibtex file Download PDF
Mathias Rudolph , "Representing Feature Changes Caused by Actions", HTW Dresden, 2010.
AbstractIn Programming by Demonstration, to solve complex tasks, a robot needs the ability to split a task into subgoals and find actions that will fulfill these subgoals. This is called planning. To be able to plan, the actions need to be stored in an inferable way. A simple generalizable method to store actions and their results is therefore one step into the direction of giving a robot the ability to solve complex tasks. This thesis proposes an approa...
Download Bibtex file Per Mail Request
1 ... 128 129 130 131 132 133 ... 181
Follow us
