An Efficiency of Optimization Method of Sign Sound Using Interactive Differential Evolution

Abstract

Interactive Evolutionary Computation is well known as an effective method to create media contents suited to user's preference and objectives to use. As one of the methods, we have already presented a method that creates sign sounds with Interactive Differential Evolution (IDE). In the user's evaluation process, the user selects better one from two presented media contents. In this study, to fundamentally investigate the efficacy of the IDE method, three listening experiments were performed, experiment 1 as comparing experiment, experiment 2 as re-evaluation for subjects themselves, and experiment 3 as re-evaluation for other subjects. Target of the creation with the IDE method was warning sign sounds. Ten males participated as subjects in the experiments. In the result of the experiment 2, gradual increase of the subjective fitness value was observed. In the result of the experiment 3, increase of the subjective fitness value was not observed. These results suggested that the IDE method has a possibility to create sign sounds suited to user's preference.