In this paper, we describe the design steps of extending LAOS, a five-layer framework for generic adaptive web learning authoring, by adding a social layer to capture (and adapt) i...
This paper focuses on a solution to better adapt ASR systems, whose language models (LM) are usually trained on topic-independent corpora, to new topics, in particular in the case...
This paper describes a simple method for significantly improving Tandem features used to train acoustic models for large-vocabulary speech recognition. The linear activations at ...
This paper introduces an edge-based object recognition method that is robust with respect to clutter, occlusion and object deformations. The method combines the use of local featu...
— In this paper we present a novel approach to robust visual servoing. This method removes the feature tracking step from a typical visual servoing algorithm. We do not need corr...