Speaker identification using pykfec and AANN

This paper presents the parameterization of speech based on amplitude and frequency modulation (AM-FM) model and its application to speaker identification. Speech parameterization is based on three different bandwidths. The speaker identification is done using auto associative neural network. The AANN is trained with SOLO speaking style speech signal, and a network is created for each speaker. The testing material used is the noisy speech signal. Different noise samples are mixed with SOLO speaking style to create noisy speech samples. The experiment shows that the feature is robust with respect to noise.