Speaker Recognition Model Based on Generalized Gamma Distribution Using Compound Transformed Dynamic Feature Vector

Abstract

In this paper, we present an efficient speaker identification system based on generalized gamma distribution. This system comprises of three basic operations, namely speech features classification and metrics for evaluation. The features extracted using MFCC are passed to shifted delta cepstral coefficients (SDC) and then applied to linear predictive coefficients (LPC) to have effective recognition. To demonstrate our method, a database is generated with 200 speakers for training and around 50 speech samples for testing.Above 90% accuracy reported.