“…Results based on different classifiers and compensators as reported in our previous results, Refs. [31][32][33] reported speaker identification performance under shouted/stressful talking conditions using the Emirati accent dataset. Their reported speaker identification performance in shouted/stressful talking conditions was 58.6%, 61.1%, 65.0%, 68%, 74.6%, 75%, 78.4%, 81.7%, 78.7%, 83.4%, and 85.8% based, respectively, on "First-Order Hidden Markov Models (HMM1s), Second-Order Hidden Markov Models (HMM2s), Third-Order Hidden Markov Models (HMM3s), Second-Order Circular Hidden Markov Models (CHMM2s), First-Order Left-to-Right Suprasegmental Hidden Markov Models (LTR-SPHMM1s), Suprasegmental Hidden Markov Models (SPHMMs), Second-Order Left-to-Right Suprasegmental Hidden Markov Models (LTRSPHMM2s), Third-Order Left-to-Right Suprasegmental Hidden Markov Models (LTRSPHMM3s), First-Order Circular Suprasegmental Hidden Markov Models (CSPHMM1s), Second-Order Circular Suprasegmental Hidden Markov Models (CSPHMM2s), and third-order circular suprasegmental hidden Markov models (CSPHMM3s)".…”