Augmented-reality visual presentation of sounds for deaf and hard of hearing people

To support deaf and hard of hearing (DHH) people by helping them detect environmental sounds in their dwellings, evaluation experiments on environmental sound recognition using a visualization device were conducted. The current study proposes an augmented reality-based system for presenting household sounds to DHH people as visual information. The effect of displaying both the icons indicating sounds classified by machine learning and a dynamic spectrogram indicating the real-time time-frequency characteristics of the environmental sounds were examined. The results confirmed that the comfort of daily life in residential spaces can be improved by combining not only the classification results of machine learning but also the real-time display of spectrograms.