ESCA Workshop on Automatic Speaker Recognition, Identification, and Verification
Artificial neural networks are applied to the problem of recognising people from their voices. With input vectors consisting of time-normalised cepstral coefficients, radial basis function networks are shown to exceed the speaker classification performance of multilayer percep-trons. With an optimised input vocabulary and the use of multiple observations, error-free results are obtained on a 50 speaker identification task.
Bibliographic reference. Fredrickson, Steven E. / Tarassenko, Lionel (1994): "Radial basis functions for speaker identification", In ASRIV-1994, 107-110.