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

Table 3

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

Video sample	1	2	3	4	5	6	7	8	Mean
Current	0.193	0.142	0.234	0.203	0.280	0.262	0.206	0.219	0.217
Previous [22]	0.219	0.181	0.236	0.239	0.273	0.284	0.219	0.205	0.232