Construction of individual identification system using voice in three-layered neural networks

We constructed an individual identification system with three-layered neural networks. Voice signals were preprocessed by Fast Fourier Transform (FFT) and, were used as input data of the neural networks with a back-propagation learning algorithm. Furthermore, we investigated the performance of the individual identification system in the neural networks. From the results, we found that the performances of the neural network were dependent on pronunciation, and that the three-layered neural networks were effective for an individual identification using voice patterns.