Automatic Embedding of Stories Into Collections of Independent Media

TL;DR

This paper presents an open-source tool that uses machine learning to embed stories into collections of independent media by analyzing tempo to create playlists that follow a narrative arc.

Contribution

It introduces a method leveraging pre-trained neural networks to extract tempo and automatically generate media collections with narrative flow.

Findings

Successfully extracts global tempo from raw audio files.

Creates playlists that follow a narrative arc based on tempo analysis.

Provides an open-source tool for automated media embedding.

Abstract

We look at how machine learning techniques that derive properties of items in a collection of independent media can be used to automatically embed stories into such collections. To do so, we use models that extract the tempo of songs to make a music playlist follow a narrative arc. Our work specifies an open-source tool that uses pre-trained neural network models to extract the global tempo of a set of raw audio files and applies these measures to create a narrative-following playlist. This tool is available at https://github.com/dylanashley/playlist-story-builder/releases/tag/v1.0.0