Abstract
This article surveys some new directions in algorithmic composition, with a special focus on the mass scale of content generation now within reach. Interest in algorithmic composition has recently flourished, including a fashion for deep learning, and commercial offshoots in apps and browser software. Whilst there is much to be excited about in recent developments, we critically survey some current directions, and likely future initiatives, of the field. In particular, the influence of and potential within music information retrieval research is highlighted, corresponding to attempts to bridge between audio machine listening and large corpus training for algorithmic composition. The scenario of mass generation is further considered, including a practical experiment in creating a billion melody data set with accompanying source code.
Highlights
1 Introduction we set out to prove that if human beings could write ‘popular music’ of poor quality at the rate of a song an hour, we could write it just as bad with a computing machine but faster (Klein 1957, p. 36)
Is one bad error of judgement enough to spoil the reputation of a computer as to all future output? How long does it take human musicians to be forgiven a musical mistake? How does a human musician re-invent themselves? Should a critical mauling of a new algorithmic composition program halt future development? Currently, the human overseers of such programs make those decisions on the programs’ behalf, but increased autonomy of MusAIcians will bring up interesting conundrums mirroring the up-and-down creative life of human musicians
Aspects of mass algorithmic composition16 have been explored in the hope that the reader may be provoked to reconsider some assumptions they may have had
Summary
There are potentially billions of content creators around the planet, working in a diverse ecosystem of historic and currently active musical styles. Given the fecundity of creation on display, uploaded every day en masse to YouTube, SoundCloud and other sharing sites, why would a generative music program have anything more to contribute? As Mute Records’ founder Daniel Miller has
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
