Speaker identification using multilayer perceptrons and radial basis function networks

This paper compares the Multilayer Perceptrons network (trained by the backpropagation) and the Radial Basis Function networks in the task of speaker identification. The experiments were carried out on 200 utterances (10 digits) of 10 speakers. LPC-derived cepstrum coefficients were used as the speaker specific features. The results showed that the Multilayer Perceptrons networks were superior in memory usage and classification time. However, they suffered from long training time and the error rate was slightly higher than that of Radial Basis Function networks.