Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Automatic Album Sequencing

Vincent Herrmann, Dylan R. Ashley, Jürgen Schmidhuber

TL;DR

A new user-friendly web-based tool that allows a less technical audience to upload music tracks, execute this technique in one click, and subsequently presents the result in a clean visualization to the user.

Abstract

Album sequencing is a critical part of the album production process. Recently, a data-driven approach was proposed that sequences general collections of independent media by extracting the narrative essence of the items in the collections. While this approach implies an album sequencing technique, it is not widely accessible to a less technical audience, requiring advanced knowledge of machine learning techniques to use. To address this, we introduce a new user-friendly web-based tool that allows a less technical audience to upload music tracks, execute this technique in one click, and subsequently presents the result in a clean visualization to the user. To both increase the number of templates available to the user and address shortcomings of previous work, we also introduce a new direct transformer-based album sequencing method. We find that our more direct method outperforms a random baseline but does not reach the same performance as the narrative essence approach. Both methods are included in our web-based user interface, and this -- alongside a full copy of our implementation -- is publicly available at https://github.com/dylanashley/automatic-album-sequencing

Automatic Album Sequencing

TL;DR

A new user-friendly web-based tool that allows a less technical audience to upload music tracks, execute this technique in one click, and subsequently presents the result in a clean visualization to the user.

Abstract

Album sequencing is a critical part of the album production process. Recently, a data-driven approach was proposed that sequences general collections of independent media by extracting the narrative essence of the items in the collections. While this approach implies an album sequencing technique, it is not widely accessible to a less technical audience, requiring advanced knowledge of machine learning techniques to use. To address this, we introduce a new user-friendly web-based tool that allows a less technical audience to upload music tracks, execute this technique in one click, and subsequently presents the result in a clean visualization to the user. To both increase the number of templates available to the user and address shortcomings of previous work, we also introduce a new direct transformer-based album sequencing method. We find that our more direct method outperforms a random baseline but does not reach the same performance as the narrative essence approach. Both methods are included in our web-based user interface, and this -- alongside a full copy of our implementation -- is publicly available at https://github.com/dylanashley/automatic-album-sequencing

Paper Structure

This paper contains 8 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. User Interface
  4. Direct Album Sequencing
  5. Method
  6. Results and Discussion
  7. Conclusion and Future Work
  8. Acknowledgments

Figures (4)

  • Figure 1: We include a full implementation of our method alongside a clean web-based user interface to make our work more accessible to a less technical audience. This implementation is available at https://github.com/dylanashley/automatic-album-sequencing
  • Figure 2: Our direct automatic album sequencer is built using a transformer architecture schlag2021linearschmidhuber1992learningvaswani2017attention. Like in the work of Ashley and Herrmann et al., the input to the network is a shuffled set of preprocessed tracks.
  • Figure 3: While it does not perform as well as the more complicated narrative essence approach, our direct transformer-based approach clearly outperforms a random baseline. This means the orders it produces are likewise viable to use for automatic album sequencing.
  • Figure :