An F-ratio based optimization technique for automatic speaker recognition system
Goutam Kumar Saha, Sandipan Chakroborty, S. Senapati · 2005
Speaker recognition needs an efficient feature extraction process and appropriate speaker model developed from these features. The work uses Fisher's F-Ratio to find discriminative ability of each individual coefficient in any feature extraction algorithm. The reduced speaker model is developed by eliminating low performing coefficients without degrading recognition ability. The result is presented on artificial neural network (ANN) based model for text-dependent recognition with two different phrases.