Abstract —In this paper, the effect of features extracted onthe performance of speaker identification engine isinvestigated. Vector Quantization (VQ) is implemented andused as identification engine. Three type of speech features,Mel Frequency Cepstral Coefficients (MFCC), PerceptualLinear Predictive (PLP), and Relative Spectral Technique-Perceptual Linear Predictive (RASTA-PLP) are extractedand used for the classification problem. One word perspeaker is used within the train phase and the identificationrate is calculated for each feature extraction technique. Thecalculation is repeated using various word of differentspoken time, and the paper specifies the feature extractiontechnique that fits with the Vector Quantization (VQ)recognition engine.

Index Terms—speaker recognition, speaker identification,vector quantization, relative spectral technique - perceptuallinear predictive (RASTA-PLP), perceptual linearprediction (PLP), mel frequency cepstral coefficients

Cite: M. Elkholy and N. Korany, "Effect of Feature Extraction Techniques on the Performance of Speaker Identification," International Journal of Signal Processing Systems,  Vol. 1, No. 1, pp. 93-97,  June 2013. doi: 10.12720/ijsps.1.1.93-97