Speaker Identication Based on Spectrogram and Local Binary Patte...

This paper presents a text-independent, closed-set speaker identification approach based on spectrogram<br>and dynamic time warping (DTW) algorithm. The preprocessed speech signals are divided into some<br>chunks, then calculated to get the magnitude of the frequency spectrum, which creates the spectrograms.<br>The local binary patterns (LBP) operator are used to obtain the LBP vectors being treated as the<br>speech features. The distances between each of the LBP vectors are measured by