Tuning a Neural Network for Harmonizing Melodies in Real-Time

We describe a sequential neural network for harmonizing melodies in real-time. T h e network models aspects of human cognition and can be used as the basis for building an interactive system that automatically generates accompaniment for simple melodies in live performance situations. T h e net learns relations between important notes of the melody and their harmonies and is able to produce harmonies for new melodies in real-time, that is, without advanced knowledge of the continuation of the melody. We tackle the challenge of evaluating these harmonies by applying distance functions to measure the disparity between the net's choice of a chord and that of the author of the source book from which the melody was taken. We experimented with three major issues that have implications on the performance of the model: searching for the best learning parameters (e.g., the decay parameters), the size of the learning set and the influence of metric information. T h e decay parameters set the scope of the short-term memory of the chords and the melody pools of units in the net. We found that the marginal benefit of a larger corpus decreases with the size of the corpus, as expected. T h e model contains a sub-net for meter that produces a periodic index of meter. T h i s sub-net provides metric organization necessary for viable interpretations of functional harmonic implications of melodic pitches. We found, indeed, that representation of metric information is essential to improve the performance of harmonization as measured by the distance function.