reservoir computing

The aim of this project is to carry out fundamental research into the application of reservoir computing (RC) for some challenging auditory pattern recognition applications such as spatial environment recognition from a multi-channel sonar signal, continuous speech recognition in background noise and instrument recognition in polyphonic music. These applications have in common that they use similar time-frequency representations of the signals and that they require an explicit dynamic behaviour of the pattern recognition system.

This EU-FP7 project aims at investigating whether it is possible to incorporate principles of human brain processing (such as self-organization, deep hierarchical processes, fast adaptation, supervised and unsupervised learning) into a new type of automatic speech recognizer. We will attempt to reach our goal by adopting the paradigm of reservoir computing because it has been demonstrated recently that this paradigm allows one to build accurate and robust (against noise) isolated digit recognizers.