Figure 1 shows an overview of our beat tracking system. BTS assumes that the time-signature of an input song is 4/4, and that its tempo is constrained to be between 65 M.M. and 185 M.M. and almost constant; these assumptions fit a large class of popular music. The emphasis in our system is on finding the temporal positions of quarter notes in audio signals rather than on tracking tempo changes; in the repertoire with which we are concerned, tempo variation is not a major factor. BTS reports beat information (BI) that consists of the beat time, its beat type, and the current tempo, in time to the input music.
The two main stages of processing are
Frequency Analysis,
in which a variety of cues are detected, and
Beat Prediction,
in which multiple hypotheses of beat positions are constructed and evaluated
(Figure 1).
In the Frequency Analysis stage,
BTS employs multiple onset-time finders that detect various cues such as
onset times in several different frequency ranges, and
onset times of two different kinds of drum-sounds:
a bass drum (BD) and a snare drum (SD).
In the Beat Prediction stage,
BTS manages multiple agents that make parallel hypotheses
based on detected onset times according to different strategies.
Each agent first calculates an inter-beat interval (IBI)
using autocorrelation
and predicts the next beat time using cross-correlation;
it then infers the beat type,
and evaluates the reliability of its own hypothesis.
The manager then determines the position of the next beat
on the basis of the most reliable hypothesis.
Finally,
in the BI Transmission stage,
BTS transmits BI to other application programs via a computer network.
The following sections describe the main stages of Frequency Analysis and Beat Prediction.
Masataka Goto
