Comparative experiments to evaluate the use of a CHMM-based speaker identification engine for Arabic spontaneous speech

In this paper, we present a comparative study between two identification engines to identify speakers automatically from their voices when speaking spontaneously in Arabic. The first engine is based on the continuous hidden Markov models (CHMMs) while the second one is based on the artificial neural networks (ANNs). The Mel frequency cepstral coefficients (MFCCs) were selected to describe the speech signal. The general Gaussian density distribution HMM was developed for the CHMM-based engine. Elman network was developed for the ANN-based engine. A series of experiments to evaluate both engines have been carried out using a subset of an arabic database. The identification rate was found to be 100% for both engines during text dependent experiments. However, for text-independent experiments, the performance for the CHMM-based engine outperformed that of the ANN-based engine. The identification rates for the CHMM- and the ANN-based engines were found to be 80% and 50%, respectively.