Neural network music composition by prediction: Exploring the benefits of psychophysical constraints and multiscale processing

In algorithmic music composition, a simple technique involves selecting notes sequentially according to a transition table that specifies the probability of the next note as a function of the previous context. I describe an extension of this transition table approach using a recurrent autopredictive connectionist network called CONCERT. CONCERT is trained on a set of pieces with the aim of extracting stylistic regularities. CONCERT can then be used to compose new pieces. A central ingredient of CONCERT is the incorporation of psychologically-grounded representations of pitch, duration, and harmonic structure. CONCERT was tested on sets of examples artificially generated according to simple rules and was shown to learn the underlying structure, even where other approaches failed. In larger experiments, CONCERT was trained on sets of J. S. Bach pieces and traditional European folk melodies and was then allowed to compose novel melodies. Although the compositions are occasionally pleasant, and are preferred over compositions generated by a third-order transition table, the compositions suffer from a lack of global coherence. To overcome this limitation, several methods are explored to permit CONCERT to induce structure at both fine and coarse scales. In experiments with a training set of waltzes, these methods yielded limited success, but the overall results cast doubt on the promise of note-by-note prediction for composition.

Retrieve postscript version of Paper
Retrieve pdf version of Paper

Unfortunately, the figures of this paper do not print correctly on some (many?) printers. I cannot help you with this, because the paper is so ancient. However I was able to track down some of the figures and put them into a separate pdf file which does print. You can retrieve them from here.

Iuri Kothe recovered some pages (pages 9, 13, 24, and 25) which would not print on his printer. You can download these here.
Return to Publications Page