Word recognition with the feature finding neural network (FFNN)

Abstract

An overview of the architecture and capabilities of the work recognizer FFNN ('feature finding neural network') is given. FFNN finds features in a self-organizing way which are relatively invariant in the presence of time distortions and changes in speaker characteristics. Fast and optimal feature selection rules have been developed to perform this task. With FFNN, essential problems of word recognition can be solved, among them a special case of the figure ground problem. FFNN is faster than the classical DTW and HMM recognizers and yields similar recognition rates.<>