Learn More
The idea of using articulatory representations for automatic speech recognition (ASR) continues to attract much attention in the speech community. Representations which are grouped under the label ''articulatory'' include artic-ulatory parameters derived by means of acoustic-articulatory transformations (inverse filtering), direct physical measurements or(More)
In order to enable the widespread use of robots in home and office environments, systems with natural interaction capabilities have to be developed. A prerequisite for natural interaction is the robot's ability to automatically recognize when and how long a person's attention is directed towards it for communication. As in open environments several persons(More)
BACKGROUND When our PC goes on strike again we tend to curse it as if it were a human being. Why and under which circumstances do we attribute human-like properties to machines? Although humans increasingly interact directly with machines it remains unclear whether humans implicitly attribute intentions to them and, if so, whether such interactions resemble(More)
The combination of multiple speech recognizers based on different signal representations is increasingly attracting interest in the speech community. In previous work we presented a hybrid speech recognition system based on the combination of acoustic and ar-ticulatory information which achieved significant word error rate reductions under highly noisy(More)
1 Introduction and the agenda of the group discussions. The concept of representation has proven useful in the study of nervous, computational and robotic systems. Examples of representation from neuroscience include descriptions of the visual system, where the activity of neurons reflect properties of the visual environment (e. representations: for example(More)
— This position paper proposes that the study of embodied cognitive agents, such as humanoid robots, can advance our understanding of the cognitive development of complex sensorimotor, linguistic and social learning skills. This in turn will benefit the design of cognitive robots capable of learning to handle and manipulate objects and tools autonomously,(More)
We present an architecture for 3D-object recognition based on the integration of neural and semantic networks. The architecture consists of mainly two components. A neural object recognition system generates object hypotheses, which are veriied or rejected by a semantic network. Thus the advantages of both paradigms are combined: in the low level eld(More)