Skip to main content
. Author manuscript; available in PMC: 2022 Nov 1.
Published in final edited form as: Proc IEEE Int Conf Acoust Speech Signal Process. 2022 Apr 27;2022:6267–6271. doi: 10.1109/icassp43922.2022.9746307

Table 2.

Results, in terms of F1-score, for depression detection on DAIC-WOZ test data comparing baseline performance and the best configuration of FrAUG selected using validation data performance. The best F1-score is boldfaced.

L,R Configuration Avg F1 Score Data
Augmentation
Baseline
L=64ms, R=50%		 0.382 None
L=64ms, 128ms
R= 50%, 25%, 10%		 0.479 5x