Emotional Video to Audio Transformation Using Deep Recurrent Neural Networks and a Neuro-Fuzzy System

Table 5

Comparison of MAE results calculated from music generated by our model and the previous one with the DEAP dataset. Note that lower values are better.

Video sample	1	2	3	4	5	6	7	8	9	10	Mean
Current	0.318	0.312	0.199	0.261	0.222	0.260	0.293	0.255	0.208	0.219	0.255
Previous [22]	0.329	0.318	0.228	0.264	0.203	0.281	0.262	0.290	0.214	0.284	0.267