Shimon the Robot Film Composer and DeepScore: An LSTM for Generation of Film Scores based on Visual Analysis

TL;DR

This paper introduces systems that leverage visual analysis to generate film scores, combining narrative understanding with aesthetic choices, including a real-time robotic composer and a software-based system for narrative-driven music creation.

Contribution

It presents novel methods integrating visual analysis with music generation, including a real-time robotic composer and a software system for narrative-based film scoring.

Findings

Real-time film scores generated by a robotic composer.

A software system producing narrative-driven film scores.

Integration of visual analysis with music generation techniques.

Abstract

Composing for a film requires developing an understanding of the film, its characters and the film aesthetic choices made by the director. We propose using existing visual analysis systems as a core technology for film music generation. We extract film features including main characters and their emotions to develop a computer understanding of the film's narrative arc. This arc is combined with visually analyzed director aesthetic choices including pacing and levels of movement. Two systems are presented, the first using a robotic film composer and marimbist to generate film scores in real-time performance. The second software-based system builds on the results from the robot film composer to create narrative driven film scores.