TOM, a new temporal neural net architecture for speech signal processing

FOR SPEECH SIGNAL PROCESSING Stéphane Durand and Frédéric Alexandre Crin-CNRS / Inria Lorraine BP 239, F-54506 Vand÷uvre-les-Nancy Cedex Nancy, France [email protected] , [email protected] ABSTRACT The neural net model TOM (Temporal Organization Map) that we present in the paper is a new connectionist approach whose time representation is di erent from the one in classical temporal connectionist models. The architecture is neurobiologically inspired and is dedicated to sensory problems involving a temporal dimension. The basic idea of the TOM model is the propagation of an activity throughout the network whose elements are organized according to a map architecture. This propagation leads to a triggering of a sequence detection. We have applied this new kind of architecture to a spoken digit recognition problem. The results draw near to the results of the best Hidden Markov Model (HMM) techniques. The interest of such an architecture is its genericity and the possibility to merge several data ows in order to improve the classical performances of neural nets.