Pitch Class Representation

A pitch class representation (Laden & Keefe, 1989; Yaremchuk & Dawson, 2008) is a kind of representation used, for instance, in neural networks that process music in an attempt to capture abstract relationships amongst notes.  In other words, it is a move away from a physically inspired representation, such as place theory (von Bekesy, 1928), where every note gets a unique representation.  In a pitch class representation only 12 input units are employed, one for each of the 12 different notes in that can appear in a scale of Western music.  Different versions of the same note (i.e., the same note played at different octaves) are all mapped onto the same input representation.  For instance, C notes belonging to different octaves are each unique pitches, each played (for instance) by pressing different piano keys, but all belong to the same pitch class – they are all C notes.  In a pitch class representation, the playing of any of these input notes would be encoded by turning on a single input unit – the one unit used to represent the pitch class of C.

References: