“…However, as in every machine learning approach, the accuracy of these systems relies highly on the quality and quantity of the available data and annotation [13]. In addition to these factors, several studies investigated how emotions are influencing facial and vocal expression in a plethora of domains such as intelligent user interfaces [14], human-human interaction [15], human-robot interaction [16], human-computer interaction [17,18], assistive in-car systems [19] and automatic speech emotion recognition [20,21,22].…”