Integration of Machine Learning algorithms in the computer-acoustic composition Goldstream Variations

Scott Deal and Javier Sanchez, co-authors, Proceedings of the 2013 International Computer Music Conference, Perth Australia

This paper presents an implementation of a musical interface that utilizes machine learning (ML) attributes in real-time performance. The objective behind the work is to empower performers with an expanded musical palette. This is achieved by employing a variation on a delay effect implemented with neural networks. In this scenario, the delayed signal is an echo of previously performed motifs based on new inputs categorized by an ART (Adaptive Resonance Theory) neural network. An overview of the piece used to test the musical range of the effect will be given, followed by a description of the development rationale for the project. The paper concludes with a qualitative evaluation of the usability and responsiveness of the effect, as well as its contribution to the aesthetic quality of the composition.