English

Automatic Embedding of Stories Into Collections of Independent Media

Computation and Language 2021-11-04 v1 Machine Learning Multimedia Sound Audio and Speech Processing

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

Keywords

Cite

@article{arxiv.2111.02216,
  title  = {Automatic Embedding of Stories Into Collections of Independent Media},
  author = {Dylan R. Ashley and Vincent Herrmann and Zachary Friggstad and Kory W. Mathewson and Jürgen Schmidhuber},
  journal= {arXiv preprint arXiv:2111.02216},
  year   = {2021}
}

Comments

2 pages in main text + 1 page of references + 6 pages of appendices, 2 figures in main text + 3 figures in appendices, 1 algorithm in appendices; source code available at https://gist.github.com/dylanashley/1387a99deb85bfc0bce11286810cd98b