MIDIVIS: Effective Music Visualization For Exploring And Evaluating Generated Alternatives In Computer-Assisted Composition
To be submitted at NIME.
Download available soon.
As generative techniques for music composition become capable of producing high volume of musical examples through approaches like batch generation, it becomes imperative for users to be able to automatically organize, explore, evaluate and compare generated alternatives. In this paper, we propose one computer-aided process for ranking and comparatively filtering music examples generated from the same given source material. We propose MIDI-Vis, a MIDI visualization tool with two exploratory functions: 1) a MIDIComp view which allows the user to visually compare the symbolic content of MIDI files. 2) MIDICluster, a t-Distributed Stochastic Neighbor Embedding (t-SNE) view to explore MIDI clusters by discriminating useful musical dimensions from MIDI files. A web-based, fully responsive system is developed using P5.js and Node.js. It is tested on MIDI corpus data, including via an integration with Calliope, computer-assisted composition (CAC) system which helps generate batches of musical variations of a given MIDI source file. The project is available here.
V. Mittal, R. Gonzalez, R.Bougueng C. Shaw, P. Pasquier, “MIDIVIS: Effective Music Visualization For Exploring And Evaluating Generated Alternatives In Computer-Assisted Composition”