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.
No takes yet. Share an insight, caveat, or question.
Saha et al. (2005) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: