An Intelligent Musical Rhythm Variation Interface
Richard Vogl, Peter Knees · 2016
The drum tracks of electronic dance music are a central and style-defining element. Yet, creating them can be a cumbersome task, mostly due to lack of appropriate tools and input devices. In this work we present an artificial-intelligence-powered software prototype, which supports musicians composing the rhythmic patterns for drum tracks. Starting with a basic pattern (seed pattern), which is provided by the user, a list of variations with varying degree of similarity to the seed pattern is generated. The variations are created using a generative stochastic neural network. The interface visualizes the patterns and provides an intuitive way to browse through them. A user study with ten experts in electronic music production was conducted to evaluate five aspects of the presented prototype. For four of these aspects the feedback was generally positive. Only regarding the use case in live environments some participants showed concerns and requested safety features.