A fundamental concern in the construction of neural nets for musical applications is the representation of input to the system. The way in which input is ultimately represented is determined by several factors: (1) the theoretical viewpoint of the researcher, (2) the primary use of the net, and (3) available computational resources. This article explores alternative representations of musical pitch and demonstrates the feasibility of these representations through the application of a neural net to a musical task - that of classifying chords as major, minor, or diminished triads. Representation is discussed from two perspectives: psychoacoustical and cognitive.
ASJC Scopus subject areas
- Media Technology
- Computer Science Applications