An Intelligent Drum Machine for Electronic Dance Music Production and Performance

Richard Vogl, and Peter Knees

Proceedings of the International Conference on New Interfaces for Musical Expression

Abstract:

An important part of electronic dance music (EDM) is the so-called beat. It is defined by the drum track of the piece and is a style defining element. While producing EDM, creating the drum track tends to be delicate, yet labor intensive work. In this work we present a touch-interface-based prototype with the goal to simplify this task. The prototype aims at supporting musicians to create rhythmic patterns in the context of EDM production and live performances. Starting with a seed pattern which is provided by the user, a list of variations with varying degree of deviation from the seed pattern is generated. The interface provides simple ways to enter, edit, visualize and browse through the patterns. Variations are generated by means of an artificial neural network which is trained on a database of drum rhythm patterns extracted from a commercial drum loop library. To evaluate the user interface and pattern generation quality a user study with experts in EDM production was conducted. It was found that participants responded positively to the user interface and the quality of the generated patterns. Furthermore, the experts consider the prototype helpful for both studio production situations and live performances.

Citation:

Richard Vogl, and Peter Knees. 2017. An Intelligent Drum Machine for Electronic Dance Music Production and Performance. Proceedings of the International Conference on New Interfaces for Musical Expression. DOI: 10.5281/zenodo.1176238

BibTeX Entry:

  @inproceedings{rvogl2017,
 abstract = {An important part of electronic dance music (EDM) is the so-called beat.  It is defined by the drum track of the piece and is a style defining element.  While producing EDM, creating the drum track tends to be delicate, yet labor intensive work.  In this work we present a touch-interface-based prototype with the goal to simplify this task.  The prototype aims at supporting musicians to create rhythmic patterns in the context of EDM production and live performances.  Starting with a seed pattern which is provided by the user, a list of variations with varying degree of deviation from the seed pattern is generated.  The interface provides simple ways to enter, edit, visualize and browse through the patterns.  Variations are generated by means of an artificial neural network which is trained on a database of drum rhythm patterns extracted from a commercial drum loop library.  To evaluate the user interface and pattern generation quality a user study with experts in EDM production was conducted.  It was found that participants responded positively to the user interface and the quality of the generated patterns.  Furthermore, the experts consider the prototype helpful for both studio production situations and live performances.},
 address = {Copenhagen, Denmark},
 author = {Richard Vogl and Peter Knees},
 booktitle = {Proceedings of the International Conference on New Interfaces for Musical Expression},
 doi = {10.5281/zenodo.1176238},
 issn = {2220-4806},
 pages = {251--256},
 publisher = {Aalborg University Copenhagen},
 title = {An Intelligent Drum Machine for Electronic Dance Music Production and Performance},
 url = {http://www.nime.org/proceedings/2017/nime2017_paper0047.pdf},
 year = {2017}
}