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

Table 1

Video excerpts distribution in the valence-arousal emotion domain for the Lindsey Stirling dataset.

Valence
Arousal	Positive	Negative	Total
High	1,359	129	1,488
Low	70	47	117
Total	1,429	176	1,605