Abstract

The paper presents an application for automatically classifying emotions in film music. A model of emotions is proposed, which is also associated with colors. The model created has nine emotional states, to which colors are assigned according to the color theory in film. Subjective tests are carried out to check the correctness of the assumptions behind the adopted emotion model. For that purpose, a statistical analysis of the subjective test results is performed. The application employs a deep convolutional neural network (CNN), which classifies emotions based on 30 s excerpts of music works presented to the CNN input using mel-spectrograms. Examples of classification results of the selected neural networks used to create the system are shown.

Highlights

  • The problem of classifying emotions in music, initiated in 1936 by Kate Hevner, is a constantly developing field of science

  • The main functions of film music are commentary, history supporting, atmosphere creating in a scene, and emotion evoking in viewers

  • Determining the emotions contained in film music is challenging but worth pursuing, as this may be used as a tool by filmmakers and composers to enhance the created picture with music

Read more

Summary

Introduction

The problem of classifying emotions in music, initiated in 1936 by Kate Hevner, is a constantly developing field of science. Music is an inseparable part of a film It occurs alongside spoken dialogue and acoustic effects, with which it forms a coherent sound layer. It is worth mentioning silence, which influences the way we perceive the surrounding sounds. Film music is characterized by its subordination to the content of the film, which makes its character change along with the mood of the scenes. Film music introduces the viewer to the atmosphere of a given film, and it reflects the emotional states and feelings of the characters. The main functions of film music are commentary, history supporting, atmosphere creating in a scene, and emotion evoking in viewers. Determining the emotions contained in film music is challenging but worth pursuing, as this may be used as a tool by filmmakers and composers to enhance the created picture with music

Objectives
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call