Table 7.

Performance comparisons of a bench model [61] and a proposed convolutional neural network (CNN) model for depression detection and Patient Health Questionnaire-9 score prediction on audio data sets in a text-dependent setting (read-dependent speech mode) and a text-independent setting (spontaneous mode; N=318).

Models	Data sets
	Text-dependent setting (mean of 10-fold)					Text-independent setting (single fold)
	ACCa (%)	F1-scoreb (%)	CCCc	RMSEd	ACC (%)		F1-score (%)	CCC	RMSE
Proposed CNNs model	78.14	77.27	0.28	9.21	56.82		37.84	0.287	5.53
GCNN-LSTMe [61]	51.65	50.90	0.43	8.10	58.57		39.78	0.497	5.70

^aACC: accuracy.

^bF₁-score: the weighted average of precision and recall.

^cCCC: Concordance Correlation Coefficient.

^dRMSE: Root Mean Square Error.

^eGCNN-LSTM: Gated Convolutional Neural Network-Long Short Term Memory.