抄録
The term presence is widely used to express the performances of audio-visual content and systems. Many advanced audio-visual systems for the perception of a higher degree of presence have been proposed. Meanwhile, methodologies for evaluating the sense of presence derived from these systems have also been discussed for the further evolution of content and systems. Although the emotion of audiences can be considered as one of the key factors in evaluating the sense of presence, the relationship between the time-series changes of the emotion and audio-visual content has not been examined so far. The authors firstly conduct subjective evaluation experiments to investigate this relationship. Based on the evaluation results and extracted audio-visual features, emotion estimation models are constructed to quantitatively estimate the time-series emotion of audiences, evoked from audio-visual content. The performance tests of the models demonstrated sufficient accuracy in estimating the emotion.