Search our Publications
Latest Publications
Martin Ernst Heckmann, Xavier Domont, Frank Joublin, Christian Goerick , "A Closer Look on Hierarchical Spectro-Temporal Features (HIST)", Proc. INTERSPEECH 2008, 2008.
AbstractSpeech recognition robust against interfering noise remains a difficult task. We previously presented a set of spectrotemporal speech features which we termed Hierarchical Spectro-Temporal (HIST) features showing improved robustness, especially when combined with RASTA-PLP. They are inspired by the receptive fields found in the mammalian auditory cortex and are organized in two hierarchical levels. A set of filters learned via ICA captures local ...
Download Bibtex file Download PDF
Till Steiner, Yaochu Jin, Bernhard Sendhoff , "A cellular model for the evolutionary development of lightweight material with an inner structure", Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2008), 2008.
AbstractWe present a model of simulated evolutionary development on the basis of cells as building blocks for growth. In this model, cells grow and interact in a three-dimensional (3D) environment, where development is controlled by a simple genome. Using cell-cell interaction such as differential adhesion, cells sort and form complex arrangements. This developmental process is evolved using a multi-objective evolutionary algorithm to achieve lightweight...
Download Bibtex file Download PDF
Xavier Domont, Martin Ernst Heckmann, Frank Joublin, Christian Goerick , "Hierarchical Spectro-Temporal Features for Robust Speech Recognition", Proc. of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 4417-4420, 2008.
AbstractPreviously we presented an auditory-inspired feed-forward architecture which achieves good performance in noisy conditions on a segmented word recognition task. In this paper we propose to use a modified version of this hierarchical model to generate features for standard Hidden Markov Models. To obtain these features we firstly compute the spectrograms using a Gammatone filterbank. A filtering over the channels permits to enhance the formant fre...
Download Bibtex file Download PDF
Stephan Kirstein, Heiko Wersing, Horst-Michael Groß, Edgar Körner , "A Vector Quantization Approach for Life-Long Learning of Categories", Proceedings of the International Conference on Neural Information Processing (ICONIP), 2008.
AbstractWe present a category learning vector quantization (cLVQ) approach for incremental and life-long learning of multiple visual categories where we focus on approaching the stability-plasticity dilemma. To achieve the life-long learning ability an incremental learning vector quantization approach is combined with a category-specific feature selection method in a novel way to allow several metrical “views” on the representation space for the same cLV...
Download Bibtex file Download PDF
Daniel Weiler, Volker Willert, Julian Eggert , "A Probabilistic Prediction Method for Object Contour Tracking", Artificial Neural Networks - ICANN, 18th International Conference, 2008.
AbstractIn this paper we present an approach for probabilistic contour prediction in an object tracking system. We combine level-set methods for image segmentation with optical flow estimations based on probability distribution functions (pdf’s) calculated at each image position. Unlike most recent level-set methods that consider exclusively the sign of the level-set function to determine an object and its background, we introduce a novel interpretation ...
Download Bibtex file Download PDF
Sven Schrader, Sonja Grün, Markus Diesmann, George L Gerstein , "Detecting synfire chain activity using massively parallel spike train recording", Journal of Neurophysiology, vol. 100, no. 4, pp. 2165–2176, 2008.
AbstractThe synfire chain model has been proposed as the substrate that underlies computational processes in the brain and has received extensive theoretical study. In this model cortical tissue is composed of a superposition of feedforward subnetworks (chains) each capable of transmitting packets of synchronized spikes with high reliability. Computations are then carried out by interactions of these chains. Experimental evidence for synfire chains has s...
Download Bibtex file Download PDF
Sven Rebhan, Florian Röhrbein, Julian Eggert, Edgar Körner , "Attention Modulation Using Short- and Long-Term Knowledge", LNCS 2008, pp. 151–160, 2008.
AbstractA fast and reliable visual search is crucial for representing visual scenes. The modulation of bottom-up attention plays an important role here. The knowledge about target features is often used to bias the bottom-up pathway. In this paper we propose a system which does not only make use of knowledge about the target features, but also uses already acquired knowledge about objects in the current scene to speed up the visual search. Main ingredien...
Download Bibtex file Download PDF
Irene Ayllón Clemente , "Investigation and Implementation of a level-set based tracking system, incorporating contour prediction by means of different, collaborating prediction algorithms", TU Darmstadt, 2008.
AbstractObject tracking is a challenging task in many computer vision applications such as automated surveillance systems, driver assistance and humanoid robots. A crucial step in object tracking is object segmentation, which is in charge of the detection of the object to track. Level set methods are a powerful approach for image segmentation. These methods are based on the iterative deformation of a surface, the level set function, which provides the co...
Download Bibtex file Per Mail Request
Tobias Rodemann, Gökhan Ince, Frank Joublin, Christian Goerick , "Using Binaural and Spectral Cues for Azimuth and Elevation Localization", IEEE-RSJ International Conference on Intelligent Robot and Systems (IROS 2008), 2008.
AbstractIt is a common assumption that with just two microphones only the azimuth angle of a sound source can be estimated and that a third, orthogonal microphone (or set of microphones) is necessary to estimate the elevation of the source. Recently, using specially designed ears and analyzing spectral cues several researchers managed to estimate sound source elevation with a binaural system. In this work, we show that with two bionic ears both azimuth a...
Download Bibtex file Download PDF
Inna Mikhailova, Martin Heracles, Bram Bolder, Herbert Janßen, Holger Brandl, Jens Schmüdderich, Christian Goerick , "Coupling of mental concepts to a reactive layer: incremental approach in system design", Proceedings of the 8th International Workshop on Epigenetic Robotics, Brighton, England, 2008.
AbstractThe design of a system that bootstraps an open-ended development is one of the most intriguing questions in Developmental Robotics. Inspired by evolution we propose an incremental design. We start with a reactive layer that provides task-unspecific interaction with the environment. We extend this initial layer by a layer of multi-modal expectation generation. The two layers are coupled by means of an active resolution of expectation mismatches. S...
Download Bibtex file Download PDF
1 ... 147 148 149 150 151 152 ... 183
Follow us
