Are Pitch-Class Profiles Really “Key for Key”?

Abstract

Most current approaches to key-finding, either from symbolic data such as MIDI or from digital audio data, rely on pitch-class profiles. Our alternative approach is based on two ideas: first, that chord progressions, understood rather loosely as pairs of neighboring harmonic states demarcated by note onsets, are sufficient as windows for key-finding, at least in the chorale context; and second, that the encapsulated identity of a chord progression (modulo pitch-class transposition and revoicing) is sufficient – that is, that reduction of progressions to pitch-class distributions is not necessary for key-finding. The system has no access to explicit information about a chord progression other than its transpositional distribution in the training corpus, yet it is able to reach an almost stunning degree of subtlety in its harmonic analysis of chorales it’s never heard before. This suggests that reductionist approaches to tonality may be off the mark, or at least that pitch-class reductionism might not be necessary for a principled account of key.