Employing Second-Order Circular Suprasegmental Hidden Markov Models to Enhance Speaker Identification Performance in Shouted Talking Environments

EURASIP Journal on Audio, Speech, and Music Processing

Table 1 Speaker identification performance in each of the neutral and shouted talking environments using the collected database based on each of LTRSPHMM1s, LTRSPHMM2s, CSPHMM1s, and CSPHMM2s.

Models	Gender	Speaker identification performance (%)
		Neutral talking environments	Shouted talking environments
LTRSPHMM1s	Male	96.6	73.5
	Female	96.8	75.7
	Average	96.7	74.6
LTRSPHMM2s	Male	97.5	78.9
	Female	97.5	77.9
	Average	97.5	78.4
CSPHMM1s	Male	97.4	78.3
	Female	98.4	79.1
	Average	97.9	78.7
CSPHMM2s	Male	98.9	82.9
	Female	98.7	83.9
	Average	98.8	83.4