Sound-effects Exploratory Retrieval System Based on Various Aspects

Abstract

The goal of this study is to develop an exploratory search system for sound effects (SEs). SEs appreciably influence viewers' impressions of a scene in a movie; thus, SE editors must skillfully select the most appropriate SEs for each scene. Existing SE search methods, however, have three main difficulties involving the diversity of SE purposes, the representation of sound using text, and the conceptualization of SEs for a given scene. These difficulties lead to inefficient SE searches because the SE editor is forced to perform repeated searches. To solve the problem, this paper proposes a framework for SE exploration under multiple perspectives. In the framework, similarities among SEs are provided to the searcher as clues for exploration. The similarities are defined by three types of features: context, acoustic features, and symbol of onomatopoeia. This paper presents the details of the framework, a system developed with the framework, function and interaction provided by the system, and the results of user observation with the system.