We have described the configuration and implementation of a real-time beat tracking system (BTS) that can deal with audio signals played on ensembles of a variety of instruments. BTS manages multiple agents that track beats according to different strategies in order to examine multiple hypotheses in parallel. This enables BTS to follow beats without losing track of them, even if some hypotheses become wrong. The use of drum patterns pre-registered as musical knowledge makes it possible to determine whether a beat is strong or weak and which note-value a beat corresponds to. The experimental results show that our beat-tracking model based on multiple-agent architecture is robust enough to handle real-world audio signals.
We plan to upgrade our beat-tracking model to understand music at a higher level and to deal with other musical genres. Future work will include a study on appropriate musical knowledge for dealing with musical audio signals, and application to various multimedia systems for which beat tracking is useful, such as video/audio editing, live ensemble, stage lighting control, and synchronization of real-time CG with music.
Masataka Goto