Spatio-Temporal Pattern Recognition with Neural Networks: Application to Speech

The processing or the recognition of non stationary process with neural networks is a challenging and yet unsolved issue. The paper discuss the general pattern recognition framework using neural networks in relation with the understanding of the peripheral auditory system. We propose a short-time structure representation of speech for speech analysis and recognition. We give examples of neural networks architecture and applications that are designed to take into account the time structure of the process to be analysed.