WAVELET-FOURIER ANALYSIS FOR SPEAKER RECOGNITION
Mariusz Zió, Jakub Gaka · 2011
An innovative method of speech analysis is described. The method shown in this paper is based on the composition of two transforms. The wavelet transform was calculated first and next the Fourier transform was applied. The wavelet-Fourier transform to representation and analysis of the speech signal is presented in this paper. This representation is used to find the differences between speakers. Speech signals were used to verify the efficiency of presented methods. It gives the possibility to analyse the efficiency of a speaker recognition system in the wavelet-Fourier domain.