Harmonising Melodies: Why do we add the bass line first?
Raymond Peter Whorley, Christophe Rhodes, Geraínt A. Wiggins, Marcus Thomas Pearce · ePrints Soton (University of Southampton) · 2013
We are taking an information theoretic approach to the question of the best way to harmonise melodies. Is it best to add the bass first, as has been traditionally the case? We describe software which uses statistical ma-chine learning techniques to learn how to harmonise from a corpus of existing music. The software is able to perform the harmonisation task in various different ways. A performance comparison using the information theoretic measure cross-entropy is able to show that, in-deed, the bass first approach appears to be best. We then use this overall strategy to investigate the performance of specialist models for the prediction of different musi-cal attributes (such as pitch and note length) compared with single models which predict all attributes. We find that the use of specialist models affords a definite per-formance advantage. Final comparisons with a simpler model show that each has its pros and cons. Some har-monisations are presented which have been generated by some of the better performing models.