Skip to main content
. Author manuscript; available in PMC: 2015 Feb 2.
Published in final edited form as: IEEE Trans Affect Comput. 2014 Oct-Dec;5(4):377–390. doi: 10.1109/TAFFC.2014.2336244

Fig. 5.

Fig. 5

There are significant differences in recognition rates between each emotion, and between each modality. When looking at a particular emotion, all differences between modality are significant (p < 0.05) except for Face vs. Audio-visual when either happy or sad is the intended emotion, and Voice vs. Face when either anger or neutral is the intended emotion.