Sound Retrieval with Intuitive Verbal Descriptions

概要

論文の詳細を見る
Our aim is to develop an intuitive and effective sound retrieval method for non-expert users. Such a retrival method should be developed to accommodate a human's perceptual features. We therefore first conducted an experiment to clarify how people represent sound. A participant listens to one sound stimulus and then conveys the sound to a partner. The results indicated that people used mostly verbal description categorized in three groups: the sound itself, the sound's situation, and the sound's impression. Based on these results, we propose three types of keywords: onomatopoeia, sound source, and adjective, which are typical keywords of the above three groups of sound description, for sound retrieval. This retrieval method was implemented for a sound database. Our method can increase the varieties of sounds able to be retrieved and allow users to intuitively search sounds because users can retrieve sounds by using keywords that are most natural to them.
社団法人電子情報通信学会の論文
2001-11-01