Table 3 Performance evaluation of different dynamic texture descriptors for the temporal stream on AVEC2013 and AVEC2014 datasets.

From: Deep spectrotemporal network based depression severity estimation from speech

Modules

AVEC2013

AVEC2014

MAE

RMSE

MAE

RMSE

MHH9 Based Temporal Stream

8.45

9.94

8.12

9.53

VLDN9 Based Temporal Stream

7.06

8.48

6.82

8.21

VLDSP16 Based Temporal Stream

7.36

8.84

7.05

8.63

VLNEP Based Temporal Stream

6.57

7.76

6.21

7.62

Back to article page