Segmentation of speech signals is a crucial task in many types of speech analysis. We present a novel approach at segmentation on a syllable level, using a Bidirectional Long-Shor...
Christian Landsiedel, Jens Edlund, Florian Eyben, ...
We investigate classification of non-linguistic vocalisations with a novel audiovisual approach and Long Short-Term Memory (LSTM) Recurrent Neural Networks as highly successful d...
The accuracy of a model to forecast a time series diminishes as the prediction horizon increases, in particular when the prediction is carried out recursively. Such decay is faster...
In this paper, we present a long term learning system for content based image retrieval over a network. Relevant feedback is used among different sessions to learn both the simila...
Contact management is an important part of everyday work. People exchange business cards to try to enter each other’s contact lists. Local businesses provide refrigerator magnet...