Generation of Variations on Theme Music Based on Impressions of Story ScenesConsidering Human′s Feeling of Music and Stories

Abstract

This paper describes a system which generates variations on theme music fitting to story scenes represented by texts and/or pictures. Inputs to the present system are original theme music and numerical information on given story scenes. The present system varies melodies, tempos, tones, tonalities, and accompaniments of given theme music based on impressions of story scenes. Genetic algorithms (GAs) using modular neural network (MNN) models as fitness functions are applied to music generation in order to reflect user's feeling of music and stories. The present system adjusts MNN models for each user on line. This paper also describes the evaluation experiments to confirm whether the generated variations on theme music reflect impressions of story scenes appropriately or not.

The Expansion of Paths in the Mutual Transformation Mechanism of Music and Narrative

“…In this area, few researches deal with the relationship between narrative and music. As the related paper, Ishizuka and Onisawa (2008) developed a system which generates the background music for a story depending upon the reader's emotional impression from each scene in the story. In contrast, music in our study is not only narrative background, and in addition we mainly focus on the structural aspect of music as opposed to the emotional aspect.…”

PhotoFeel

“…The diverse feelings conveyed from the photos are not considered. Although the works [7][8] exploited music generation and accompaniment to present the feelings expressed in visual contents, they primarily riveted on illustrations and paintings, respectively. In this paper, we propose a novel audiovisual system, PhotoFeel, for users to not only browse the visual contents easily but also taste the feelings conveyed by the given collection of photos.…”