Real - time Rhythm Tracking for Drumless Audio Signals

This paper presents a real-time rhythm tracking system that recognizes a rhythmic structure in musical audio signals without drum-sounds. Most previous systems dealt with MIDI signals and had di culty in processing, in real time, audio signals containing sounds of various instruments and in tracking rhythm above the quarter-note level. Our system not only tracks beats at the quarter-note level but also recognizes rhythmic structure at the half-note and measure levels. To make musical decisions about the audio signals, we propose a method of detecting chord changes that does not rely on chord name identi cation. The method enables the system to understand music at di erent rhythmic levels | for example, to nd the beginnings of half notes and measures | and to select the best of various hypotheses about beat positions. Experimental results show that our system is robust enough to handle audio signals sampled from compact discs of popular music.