Wavelet feature selection based neural networks with application to the text independent speaker identification

A wavelet packets feature selection derived by using neuro-fuzzy evaluation index for speaker identification is described. The concept of a flexible membership function incorporating weighed distance is introduced in the evaluation index to make the modeling of clusters more appropriate. Experimental evaluation of the systems performance was conducted on three speech databases. Our results have shown that this feature selection introduced better performance than the wavelet features with respect to the percentages of recognition.