Predicting user mental states in spoken dialogue systems

EURASIP Journal on Advances in Signal Processing

Table 4 Results of the high-level dialogue features defined for the comparison of the mental-state and UAH baseline systems

Description of the metrics in Table 3	Simulated users				Recruited users
	Baseline		Mental-state		Baseline		Mental-state
	S1	S2	S1	S2	S1	S2	S1	S2
%success	78	66	87	76	87	83	97	95
n CE	0.76	0.71	0.89	0.84	0.85	0.80	0.91	0.88
n NCE	0.21	0.24	0.09	0.11	0.18	0.20	0.09	0.08
%ECR	79	75	91	88	82	80	92	91
avgturn/dial	8.4	14.8	4.7	9.2	9.2	15.1	5.8	10.4
%diff	76	88	67	84	77	93	76	91
#repMS	7	3	9	7	5	2	8	4
#turnsMS	2	9	2	7	2	9	2	7
#turnsSh	2	7	2	7	2	7	2	7
#turnsLo	14	20	12	18	12	17	9	15