The goal of this paper is to present a system that automatically extracts metadata from polyphonic audio signals. This metadata is related to the tonal content of music. It can be used to characterize the tonal space of a piece, understood as the relationships between pitches, chords and keys, in accordance with the principles and procedures of tonality. These features are relevant in the context of music similarity and content search, retrieval and navigation across digital music collections.
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.